Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Opus 4.8 dadccb9264 refactor: rip out the legacy TrackedRepository / repositories path
CI / Check (pull_request) Successful in 5m29s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
Onboarded targets are now the sole persisted entity. The legacy
`TrackedRepository` model, the `repositories` collection, the `/repositories`
API, the Repositories dashboard page, the one-shot migration, and the
`UNIFIED_PIPELINE` transition flag are all removed. Net −1.7k LOC.

Agent
- New internal `pipeline::repo_view::RepoView` (non-persisted) replaces the
  `TrackedRepository` model; it's projected from an `OnboardedTarget` + its code
  artifact by `RepoView::from_target` (the old `repo_view_from_target`), so the
  scan/PR-review pipeline is byte-for-byte the same behaviour it already ran on
  the unified path — only the type's origin changed.
- `run_scan` always runs the unified `run_target`; the legacy `orchestrator::run`
  and the `unified_pipeline` flag are gone. `run_pr_review` resolves the target
  from `onboarded_targets`.
- Webhooks (github/gitea/gitlab), the CVE monitor, graph build, chat embeddings,
  health stats, and the pentest repo lookup all read `onboarded_targets`.
- `delete_target` now cascades the full downstream set (findings, sbom, scans,
  cve, tracker issues, graph, embeddings, DAST targets + pentest sessions and
  their children) — matching the old repository delete.
- `get_ssh_public_key` moved to the health handler; `repositories()` accessor,
  `repos.rs`, and `migrate/` deleted.

Core
- `TrackedRepository` removed; `ScanTrigger` stays. `unified_pipeline` config
  field removed.

Dashboard
- Repositories page + route deleted; overview / graph / chat / pentest-wizard
  read onboarded targets; `infrastructure/repositories.rs` trimmed to just the
  SSH-key fetch.

Tests
- Legacy repositories-API and migration integration tests removed; tenant
  isolation, cascade-delete, and stats tests repointed to `/targets` /
  `onboarded_targets`. `git.rs` gains a `sanitize_repo_dir` unit test.

Local: fmt clean; agent/mcp clippy clean; dashboard server+web compile; core +
agent lib tests (32) pass; integration tests compile.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-13 21:17:41 +02:00
37 changed files with 144 additions and 5566 deletions
Generated
+8 -15
View File
@@ -679,7 +679,6 @@ dependencies = [
"rand 0.9.2",
"regex",
"reqwest",
"roxmltree",
"secrecy",
"serde",
"serde_json",
@@ -2104,7 +2103,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [
"libc",
"windows-sys 0.61.2",
"windows-sys 0.52.0",
]
[[package]]
@@ -3699,7 +3698,7 @@ version = "0.50.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
dependencies = [
"windows-sys 0.61.2",
"windows-sys 0.60.2",
]
[[package]]
@@ -4629,12 +4628,6 @@ dependencies = [
"syn",
]
[[package]]
name = "roxmltree"
version = "0.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c20b6793b5c2fa6553b250154b78d6d0db37e72700ae35fad9387a46f487c97"
[[package]]
name = "rust-stemmers"
version = "1.2.0"
@@ -4686,7 +4679,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.4.15",
"windows-sys 0.59.0",
"windows-sys 0.52.0",
]
[[package]]
@@ -4699,7 +4692,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.12.1",
"windows-sys 0.61.2",
"windows-sys 0.52.0",
]
[[package]]
@@ -5222,7 +5215,7 @@ version = "0.8.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
dependencies = [
"heck 0.5.0",
"heck 0.4.1",
"proc-macro2",
"quote",
"syn",
@@ -5577,10 +5570,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "82a72c767771b47409d2345987fda8628641887d5466101319899796367354a0"
dependencies = [
"fastrand",
"getrandom 0.4.1",
"getrandom 0.3.4",
"once_cell",
"rustix 1.1.4",
"windows-sys 0.61.2",
"windows-sys 0.52.0",
]
[[package]]
@@ -6753,7 +6746,7 @@ version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [
"windows-sys 0.61.2",
"windows-sys 0.48.0",
]
[[package]]
+1 -1
View File
@@ -23,7 +23,7 @@ tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
chrono = { version = "0.4", features = ["serde"] }
mongodb = { version = "3", features = ["rustls-tls", "compat-3-0-0"] }
reqwest = { version = "0.12", features = ["json", "rustls-tls", "multipart"], default-features = false }
reqwest = { version = "0.12", features = ["json", "rustls-tls"], default-features = false }
thiserror = "2"
sha2 = "0.10"
hex = "0.4"
+2 -4
View File
@@ -34,7 +34,7 @@ hex = { workspace = true }
uuid = { workspace = true }
secrecy = { workspace = true }
regex = { workspace = true }
axum = { version = "0.8", features = ["multipart"] }
axum = "0.8"
tower-http = { version = "0.6", features = ["cors", "trace", "set-header"] }
git2 = "0.20"
octocrab = "0.44"
@@ -42,8 +42,6 @@ tokio-cron-scheduler = "0.13"
dotenvy = "0.15"
hmac = "0.12"
walkdir = "2"
# Read-only XML tree parsing for PLCopen project files (POU extraction).
roxmltree = "0.20"
base64 = "0.22"
urlencoding = "2"
futures-util = "0.3"
@@ -65,5 +63,5 @@ tokio = { workspace = true }
mongodb = { workspace = true }
uuid = { workspace = true }
secrecy = { workspace = true }
axum = { version = "0.8", features = ["multipart"] }
axum = "0.8"
tower-http = { version = "0.6", features = ["cors"] }
+1 -111
View File
@@ -5,7 +5,7 @@
use std::collections::HashMap;
use std::sync::Arc;
use axum::extract::{Extension, Multipart, Path, Query};
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId, to_bson};
@@ -377,116 +377,6 @@ pub async fn add_artifact(
get_target(Extension(agent), tenant, Path(id)).await
}
/// POST /api/v1/targets/{id}/artifacts/upload — attach an artifact by uploading
/// its file (PLC project, firmware image, source archive, mobile package). The
/// bytes are written to the artifact blob store and referenced by `stored_path`,
/// so ingest resolves them locally (no URL fetch).
///
/// Multipart fields: `file` (required), `kind` (required, snake_case
/// `ArtifactKind`), `plc_format` (optional, for PLC projects).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn upload_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
mut multipart: Multipart,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
if db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.is_none()
{
return Err(StatusCode::NOT_FOUND);
}
let mut kind: Option<ArtifactKind> = None;
let mut plc_format: Option<PlcFormat> = None;
let mut filename = String::from("upload.bin");
let mut bytes: Option<axum::body::Bytes> = None;
while let Some(field) = multipart
.next_field()
.await
.map_err(|_| StatusCode::BAD_REQUEST)?
{
match field.name().unwrap_or("") {
"kind" => {
let v = field.text().await.map_err(|_| StatusCode::BAD_REQUEST)?;
kind = parse_enum(&v);
}
"plc_format" => {
let v = field.text().await.map_err(|_| StatusCode::BAD_REQUEST)?;
plc_format = parse_enum(&v);
}
"file" => {
if let Some(fname) = field.file_name() {
filename = fname.to_string();
}
bytes = Some(field.bytes().await.map_err(|_| StatusCode::BAD_REQUEST)?);
}
_ => {}
}
}
let (Some(kind), Some(bytes)) = (kind, bytes) else {
return Err(StatusCode::BAD_REQUEST);
};
// Store the uploaded bytes under the artifact blob store.
let safe_name: String = filename
.chars()
.map(|c| {
if c.is_ascii_alphanumeric() || matches!(c, '.' | '-' | '_') {
c
} else {
'_'
}
})
.collect();
let dir = std::path::Path::new(&agent.config.artifact_store_base_path)
.join("uploads")
.join(&id);
std::fs::create_dir_all(&dir).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let dest = dir.join(format!("{}_{safe_name}", uuid::Uuid::new_v4()));
std::fs::write(&dest, bytes.as_ref()).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Build the artifact for this kind, referencing the stored file.
let mut artifact = match kind {
ArtifactKind::PlcProject => Artifact::plc_project(
filename.clone(),
plc_format.unwrap_or(PlcFormat::PlcopenXml),
),
ArtifactKind::FirmwareImage => Artifact::firmware_image(filename.clone()),
ArtifactKind::SourceArchive => Artifact::source_archive(filename.clone()),
ArtifactKind::MobilePackage => Artifact::mobile_package(filename.clone()),
// Non-file kinds (git repo, live URL, container ref, text) use the JSON
// add-artifact endpoint, not upload.
_ => return Err(StatusCode::BAD_REQUEST),
};
artifact.stored_path = Some(dest.to_string_lossy().to_string());
artifact.size_bytes = Some(bytes.len() as u64);
let artifact_bson = to_bson(&artifact).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact_bson }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// Deserialize a snake_case enum value from a plain string.
fn parse_enum<T: for<'de> Deserialize<'de>>(s: &str) -> Option<T> {
serde_json::from_value(serde_json::Value::String(s.to_string())).ok()
}
/// GET /api/v1/targets/{id}/applicable-scans — the scan-applicability matrix.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn applicable_scans_for_target(
-4
View File
@@ -26,10 +26,6 @@ pub fn build_router() -> Router {
"/api/v1/targets/{id}/artifacts",
post(handlers::onboarding::add_artifact),
)
.route(
"/api/v1/targets/{id}/artifacts/upload",
post(handlers::onboarding::upload_artifact),
)
.route(
"/api/v1/targets/{id}/applicable-scans",
get(handlers::onboarding::applicable_scans_for_target),
+1 -4
View File
@@ -1,6 +1,6 @@
use std::sync::Arc;
use axum::extract::{DefaultBodyLimit, Request};
use axum::extract::Request;
use axum::http::HeaderValue;
use axum::middleware::Next;
use axum::response::Response;
@@ -74,9 +74,6 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
let mut app = routes::build_router()
.merge(admin_router)
// Allow large artifact uploads (PLC .projectarchive, firmware images,
// mobile packages) — axum's default request-body limit is only 2 MiB.
.layer(DefaultBodyLimit::max(512 * 1024 * 1024))
.layer(Extension(Arc::new(agent.clone())))
.layer(CorsLayer::permissive())
.layer(TraceLayer::new_for_http())
+2 -84
View File
@@ -162,29 +162,16 @@ fn ingest_blob(
match blob::extract_zip(&stored, &dest) {
Ok(()) => dest,
Err(e) => {
// Not a zip container — this is a single uploaded file (e.g. a
// `.st`/`.xml` PLC project or a `.tar.gz`). The content-addressed
// blob has no extension, so materialize it into a working dir
// under its original name; extension-based scanners (PLC) can then
// discover it and report a readable path.
// Not a zip (e.g. a tar.gz source archive) — keep the blob and
// note it so later stages can decide what to do.
facts.push(DetectedFact::new(
"archive_unextracted",
e.to_string(),
"ingest",
));
match materialize_single(&stored, &dest, &blob_file_name(artifact)) {
Ok(dir) => dir,
Err(copy_err) => {
facts.push(DetectedFact::new(
"materialize_failed",
copy_err.to_string(),
"ingest",
));
stored.clone()
}
}
}
}
} else {
stored.clone()
};
@@ -199,27 +186,6 @@ fn ingest_blob(
})
}
/// Copy a stored blob into `dest`/`name`, returning `dest`. Used when an
/// "extractable" artifact turns out to be a single file rather than an archive.
fn materialize_single(stored: &Path, dest: &Path, name: &str) -> Result<PathBuf, AgentError> {
std::fs::create_dir_all(dest)?;
std::fs::copy(stored, dest.join(name))?;
Ok(dest.to_path_buf())
}
/// A safe, single-segment file name for an artifact, preserving the original
/// extension so scanners can identify it. Derives from `source_ref` (the
/// uploaded/original file name); `file_name` strips any directory components,
/// so this is traversal-safe. Falls back to the artifact id.
fn blob_file_name(artifact: &Artifact) -> String {
Path::new(&artifact.source_ref)
.file_name()
.and_then(|n| n.to_str())
.map(str::to_string)
.filter(|s| !s.is_empty())
.unwrap_or_else(|| format!("artifact-{}", artifact.id))
}
/// An artifact with no on-disk form: record a single fact, no hash/path.
fn metadata_only(artifact: &Artifact, fact: DetectedFact) -> IngestedArtifact {
IngestedArtifact {
@@ -365,52 +331,4 @@ mod tests {
assert_eq!(creds.ssh_key_path.as_deref(), Some("/default/ssh/key"));
assert!(creds.auth_token.is_none());
}
/// A single uploaded PLC file (not an archive) must land in a working dir
/// under its original name so the PLC scanner can discover it by extension
/// and report a readable path — the demo's upload → scan path.
#[test]
fn single_uploaded_plc_file_is_materialized_and_scannable() {
use compliance_core::models::PlcFormat;
let scratch = Scratch::new();
let store = scratch.0.join("store");
// Simulate the upload handler: bytes written to an `uploads/` path,
// `source_ref` carrying the original (clean) file name.
let uploads = scratch.0.join("uploads");
std::fs::create_dir_all(&uploads).expect("mkdir uploads");
let uploaded = uploads.join("a1b2c3_pump_station.st");
std::fs::write(
&uploaded,
"PROGRAM P\nVAR\n ApiKey : STRING := 'sk-live-1234';\nEND_VAR\nEND_PROGRAM\n",
)
.expect("write st");
let mut artifact = Artifact::plc_project("pump_station.st", PlcFormat::StructuredText);
artifact.stored_path = Some(uploaded.to_string_lossy().to_string());
let ctx = ctx_for(&store, "t-plc");
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
// Working path is a directory (not the extensionless blob) holding the
// file under its original name.
let wp = out.working_path.expect("working path");
assert!(wp.is_dir(), "expected a working dir, got {wp:?}");
assert!(wp.join("pump_station.st").is_file());
// The PLC scanner finds the hardcoded credential and reports a clean path.
let findings = crate::pipeline::plc::analyze_tree(&wp, "t-plc");
assert!(
!findings.is_empty(),
"scanner should flag the uploaded file"
);
assert!(findings
.iter()
.any(|f| f.rule_id.as_deref() == Some("plc-hardcoded-credential")));
assert_eq!(
findings[0].file_path.as_deref(),
Some("pump_station.st"),
"finding should reference the original file name"
);
}
}
-283
View File
@@ -204,202 +204,6 @@ impl CveScanner {
Ok(results)
}
/// Match the CODESYS **runtime** component against NVD by CPE.
///
/// CODESYS advisories (the CoDe16 cluster and friends) are indexed in NVD by
/// CPE (`cpe:2.3:a:codesys:control*`) keyed off the *runtime* version — not by
/// the internal `Cmp*`/`Sys*` library names OSV-by-purl would look up. So we
/// find the runtime SBOM entry, pull every `cpe:2.3:a:codesys:*` CVE from NVD,
/// and keep the ones whose affected-version range covers our runtime version.
/// Best-effort: returns empty without an NVD key, on a network error, or when
/// no CODESYS runtime component is present.
pub async fn scan_codesys(&self, repo_id: &str, entries: &mut [SbomEntry]) -> Vec<CveAlert> {
let Some((name, version)) = codesys_runtime(entries) else {
return Vec::new();
};
let url = "https://services.nvd.nist.gov/rest/json/cves/2.0\
?virtualMatchString=cpe:2.3:a:codesys";
let mut req = self.http.get(url);
if let Some(key) = &self.nvd_api_key {
req = req.header("apiKey", key.as_str());
}
let body: serde_json::Value = match req.send().await {
Ok(r) if r.status().is_success() => match r.json().await {
Ok(b) => b,
Err(e) => {
tracing::warn!("CODESYS NVD parse failed: {e}");
return Vec::new();
}
},
Ok(r) => {
tracing::warn!("CODESYS NVD returned {}", r.status());
return Vec::new();
}
Err(e) => {
tracing::warn!("CODESYS NVD request failed: {e}");
return Vec::new();
}
};
let matched = parse_codesys_nvd(&body, &version);
let mut alerts = Vec::new();
for cve in matched {
if let Some(e) = entries
.iter_mut()
.find(|e| e.name == name && e.version == version)
{
e.known_vulnerabilities.push(VulnRef {
id: cve.id.clone(),
source: "nvd".to_string(),
severity: None,
url: Some(format!("https://nvd.nist.gov/vuln/detail/{}", cve.id)),
});
}
let mut alert = CveAlert::new(
cve.id,
repo_id.to_string(),
name.clone(),
version.clone(),
CveSource::Nvd,
);
alert.summary = cve.summary;
alert.cvss_score = cve.cvss;
alerts.push(alert);
}
tracing::info!(runtime = %name, version = %version, cves = alerts.len(), "CODESYS CVE match");
alerts
}
}
/// The CODESYS runtime component (name + version) from an SBOM, if present. The
/// runtime carries the version CODESYS advisories key off; the internal library
/// components do not.
fn codesys_runtime(entries: &[SbomEntry]) -> Option<(String, String)> {
entries
.iter()
.find(|e| e.package_manager == "codesys" && e.name.starts_with("CODESYS Control"))
.map(|e| (e.name.clone(), e.version.clone()))
}
/// A parsed NVD CVE that affects the CODESYS runtime.
struct CodesysCve {
id: String,
summary: Option<String>,
cvss: Option<f64>,
}
/// Version constraints from an NVD `cpeMatch` node.
#[derive(Default)]
struct CpeRange {
exact: Option<String>,
start_incl: Option<String>,
start_excl: Option<String>,
end_incl: Option<String>,
end_excl: Option<String>,
}
/// Parse an NVD CVE-list response and keep the CVEs whose CODESYS CPE match covers
/// `runtime_version`.
fn parse_codesys_nvd(body: &serde_json::Value, runtime_version: &str) -> Vec<CodesysCve> {
let mut out = Vec::new();
let Some(vulns) = body["vulnerabilities"].as_array() else {
return out;
};
for v in vulns {
let cve = &v["cve"];
let Some(id) = cve["id"].as_str() else {
continue;
};
let covered = cve["configurations"]
.as_array()
.into_iter()
.flatten()
.flat_map(|c| c["nodes"].as_array().into_iter().flatten())
.flat_map(|n| n["cpeMatch"].as_array().into_iter().flatten())
.any(|cm| {
cm["vulnerable"].as_bool() == Some(true)
&& cm["criteria"]
.as_str()
.is_some_and(|c| c.contains(":codesys:"))
&& version_matches(runtime_version, &cpe_range(cm))
});
if covered {
let summary = cve["descriptions"]
.as_array()
.and_then(|d| d.iter().find(|x| x["lang"].as_str() == Some("en")))
.and_then(|x| x["value"].as_str())
.map(String::from);
let cvss = cve["metrics"]["cvssMetricV31"]
.as_array()
.and_then(|m| m.first())
.and_then(|m| m["cvssData"]["baseScore"].as_f64());
out.push(CodesysCve {
id: id.to_string(),
summary,
cvss,
});
}
}
out
}
/// Build a [`CpeRange`] from an NVD `cpeMatch` object.
fn cpe_range(cm: &serde_json::Value) -> CpeRange {
let exact = cm["criteria"]
.as_str()
.and_then(cpe_version)
.filter(|v| v != "*" && v != "-" && !v.is_empty());
CpeRange {
exact,
start_incl: cm["versionStartIncluding"].as_str().map(String::from),
start_excl: cm["versionStartExcluding"].as_str().map(String::from),
end_incl: cm["versionEndIncluding"].as_str().map(String::from),
end_excl: cm["versionEndExcluding"].as_str().map(String::from),
}
}
/// The version field (6th component) of a CPE 2.3 string.
fn cpe_version(criteria: &str) -> Option<String> {
criteria.split(':').nth(5).map(String::from)
}
/// Whether `v` satisfies a CPE version range.
fn version_matches(v: &str, r: &CpeRange) -> bool {
use std::cmp::Ordering::{Equal, Greater, Less};
if let Some(exact) = &r.exact {
return cmp_dotted(v, exact) == Equal;
}
let mut ok = true;
if let Some(s) = &r.start_incl {
ok &= cmp_dotted(v, s) != Less;
}
if let Some(s) = &r.start_excl {
ok &= cmp_dotted(v, s) == Greater;
}
if let Some(e) = &r.end_incl {
ok &= cmp_dotted(v, e) != Greater;
}
if let Some(e) = &r.end_excl {
ok &= cmp_dotted(v, e) == Less;
}
ok
}
/// Compare two dotted numeric versions (`4.17.0.0` vs `4.9.0.0`); missing
/// components count as 0, non-numeric components as 0.
fn cmp_dotted(a: &str, b: &str) -> std::cmp::Ordering {
let pa: Vec<u64> = a.split('.').map(|x| x.parse().unwrap_or(0)).collect();
let pb: Vec<u64> = b.split('.').map(|x| x.parse().unwrap_or(0)).collect();
for i in 0..pa.len().max(pb.len()) {
let x = pa.get(i).copied().unwrap_or(0);
let y = pb.get(i).copied().unwrap_or(0);
match x.cmp(&y) {
std::cmp::Ordering::Equal => continue,
other => return other,
}
}
std::cmp::Ordering::Equal
}
#[derive(serde::Deserialize)]
@@ -424,90 +228,3 @@ struct OsvVuln {
summary: Option<String>,
severity: Option<String>,
}
#[cfg(test)]
mod tests {
use super::*;
use std::cmp::Ordering::{Equal, Greater, Less};
fn entry(name: &str, ver: &str, pm: &str) -> SbomEntry {
SbomEntry::new("t".into(), name.into(), ver.into(), pm.into())
}
#[test]
fn finds_the_codesys_runtime_component() {
let entries = vec![
entry("Standard", "3.5.18.0", "codesys"),
entry("CODESYS Control for Linux ARM SL", "4.17.0.0", "codesys"),
];
assert_eq!(
codesys_runtime(&entries),
Some(("CODESYS Control for Linux ARM SL".into(), "4.17.0.0".into()))
);
// Internal library components are not the runtime.
assert!(codesys_runtime(&[entry("Util", "3.5.21.0", "codesys")]).is_none());
}
#[test]
fn dotted_version_comparison() {
assert_eq!(cmp_dotted("4.17.0.0", "4.9.0.0"), Greater);
assert_eq!(cmp_dotted("4.9.0.0", "4.17.0.0"), Less);
assert_eq!(cmp_dotted("3.5.18.0", "3.5.18.0"), Equal);
assert_eq!(cmp_dotted("4.2", "4.2.0.0"), Equal); // missing components = 0
}
#[test]
fn version_range_matching() {
let end_excl = CpeRange {
end_excl: Some("4.9.0.0".into()),
..Default::default()
};
assert!(!version_matches("4.17.0.0", &end_excl)); // patched
assert!(version_matches("4.5.0.0", &end_excl)); // affected
let exact = CpeRange {
exact: Some("3.5.16.0".into()),
..Default::default()
};
assert!(version_matches("3.5.16.0", &exact));
assert!(!version_matches("3.5.17.0", &exact));
let span = CpeRange {
start_incl: Some("3.0.0.0".into()),
end_incl: Some("3.5.16.0".into()),
..Default::default()
};
assert!(version_matches("3.5.16.0", &span));
assert!(!version_matches("3.5.17.0", &span));
}
#[test]
fn parses_nvd_and_matches_by_runtime_version() {
// Two CODESYS CVEs: one affects < 4.9 (our 4.17 is patched), one affects
// <= 4.20 (our 4.17 is affected). Only the latter should match.
let body = serde_json::json!({
"vulnerabilities": [
{"cve": {"id":"CVE-2023-0001",
"descriptions":[{"lang":"en","value":"old CmpBlkDrvTcp bug"}],
"metrics":{"cvssMetricV31":[{"cvssData":{"baseScore":7.5}}]},
"configurations":[{"nodes":[{"cpeMatch":[
{"vulnerable":true,
"criteria":"cpe:2.3:a:codesys:control_for_linux_sl:*:*:*:*:*:*:*:*",
"versionEndExcluding":"4.9.0.0"}
]}]}]}},
{"cve": {"id":"CVE-2024-0002",
"descriptions":[{"lang":"en","value":"recent runtime bug"}],
"metrics":{"cvssMetricV31":[{"cvssData":{"baseScore":9.8}}]},
"configurations":[{"nodes":[{"cpeMatch":[
{"vulnerable":true,
"criteria":"cpe:2.3:a:codesys:control_for_linux_sl:*:*:*:*:*:*:*:*",
"versionEndIncluding":"4.20.0.0"}
]}]}]}}
]
});
let matched = parse_codesys_nvd(&body, "4.17.0.0");
let ids: Vec<&str> = matched.iter().map(|c| c.id.as_str()).collect();
assert_eq!(ids, vec!["CVE-2024-0002"]);
assert_eq!(matched[0].cvss, Some(9.8));
}
}
@@ -1,95 +0,0 @@
//! Minimal EtherNet/IP (CIP) reachability probe.
//!
//! Sends an EtherNet/IP encapsulation **ListIdentity** command (0x0063) over TCP
//! 44818 and checks for a valid encapsulation reply — confirming a CIP device
//! without opening a session or writing anything.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of an EtherNet/IP handshake probe.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct EnipProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint returned a valid EtherNet/IP encapsulation reply.
pub is_enip: bool,
}
/// Probe an EtherNet/IP endpoint with a ListIdentity request. Read-only.
pub async fn probe(host: &str, port: u16, budget: Duration) -> EnipProbe {
let mut out = EnipProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out;
};
out.reachable = true;
// Encapsulation header (24 bytes): command(2) length(2) session(4) status(4)
// context(8) options(4). ListIdentity = command 0x0063, everything else zero.
let mut req = vec![0u8; 24];
req[0..2].copy_from_slice(&0x0063u16.to_le_bytes());
if timeout(budget, stream.write_all(&req))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
let mut hdr = [0u8; 24];
if timeout(budget, stream.read_exact(&mut hdr))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
let command = u16::from_le_bytes([hdr[0], hdr[1]]);
let status = u32::from_le_bytes([hdr[8], hdr[9], hdr[10], hdr[11]]);
// Echoed command + success status = a valid EtherNet/IP encapsulation reply.
if command == 0x0063 && status == 0 {
out.is_enip = true;
}
out
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
async fn mock_server() -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
let mut req = [0u8; 24];
if sock.read_exact(&mut req).await.is_err() {
return;
}
// Reply: echo command 0x0063, status 0, no data.
let mut hdr = vec![0u8; 24];
hdr[0..2].copy_from_slice(&0x0063u16.to_le_bytes());
let _ = sock.write_all(&hdr).await;
});
addr
}
#[tokio::test]
async fn probe_detects_an_ethernetip_device() {
let addr = mock_server().await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.is_enip);
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.is_enip);
}
}
-273
View File
@@ -1,273 +0,0 @@
//! Dynamic ICS (industrial control system) probing for PLC/SPS targets.
//!
//! Where the control-logic scanner is static (over ST / PLCopen XML), this probes
//! the *running* device over industrial protocols and reports exposed /
//! unauthenticated control interfaces. It is read-only: it never writes to a live
//! process. Modbus/TCP and OPC UA are implemented; EtherNet-IP is a follow-on.
pub mod ethernetip;
pub mod modbus;
pub mod opcua;
pub mod portscan;
use std::time::Duration;
use compliance_core::models::{Finding, ScanType, Severity};
use crate::pipeline::dedup;
/// Well-known deep-probe ports (each independent of any WebVisu HTTP port).
const MODBUS_PORT: u16 = 502;
const OPCUA_PORT: u16 = 4840;
const ENIP_PORT: u16 = 44818;
/// Probe a PLC/SPS device's industrial-protocol surface and return findings.
/// Read-only. Deep-probes Modbus/TCP, OPC UA and EtherNet/IP, plus a service
/// discovery scan of the remaining OT / insecure-management ports. `endpoint` is
/// the target's live-URL / host reference.
pub async fn probe_target(endpoint: &str, repo_id: &str, budget: Duration) -> Vec<Finding> {
let (host, modbus_port) = parse_endpoint(endpoint);
let mut findings = modbus_findings(&host, modbus_port, repo_id, budget).await;
findings.extend(opcua_findings(&host, OPCUA_PORT, repo_id, budget).await);
findings.extend(enip_findings(&host, ENIP_PORT, repo_id, budget).await);
findings.extend(portscan_findings(&host, repo_id, budget).await);
findings
}
/// Findings from probing the Modbus/TCP surface.
async fn modbus_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = modbus::probe(host, port, budget).await;
let mut findings = Vec::new();
if !probe.speaks_modbus {
// Not reachable, or the port does not speak Modbus — nothing to report.
return findings;
}
let target = format!("{host}:{port}");
// Reachable Modbus/TCP = unauthenticated, cleartext control access by design.
let fp = dedup::compute_fingerprint(&[repo_id, "ics-modbus-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"Modbus/TCP control interface exposed without authentication".to_string(),
format!(
"The device at {target} answers Modbus/TCP requests. Modbus/TCP has no \
authentication or encryption in the protocol, so any host that can reach this \
port can read and write process variables (coils/registers) and disrupt the \
controlled process."
),
Severity::Critical,
);
f.rule_id = Some("ics-modbus-exposed".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Restrict the Modbus/TCP port to a trusted control network (segmentation / \
firewall / VPN), never expose it to IT or the internet, and prefer an authenticated \
transport (e.g. Modbus/TLS) or a secure protocol gateway where available."
.to_string(),
);
findings.push(f);
if let Some(dev) = &probe.device {
let details = [
dev.vendor.as_deref(),
dev.product.as_deref(),
dev.revision.as_deref(),
]
.into_iter()
.flatten()
.collect::<Vec<_>>()
.join(" / ");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-device-disclosure", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"PLC device identity disclosed over Modbus".to_string(),
format!(
"The device at {target} discloses its identity via Modbus Read Device \
Identification: {details}. This aids fingerprinting and targeting of \
known-vulnerable firmware/runtime versions."
),
Severity::Low,
);
f.rule_id = Some("ics-device-disclosure".to_string());
f.cwe = Some("CWE-200".to_string());
f.remediation = Some(
"Limit network reach to the device; Modbus device identification cannot be \
disabled, so exposure is bounded by network segmentation."
.to_string(),
);
findings.push(f);
}
findings
}
/// Findings from probing the OPC UA surface (default port 4840). A reachability
/// probe only: it flags an exposed OPC UA server for review of its security
/// policy / authentication (deep SecurityPolicy analysis is a follow-on).
async fn opcua_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = opcua::probe(host, port, budget).await;
let mut findings = Vec::new();
if !probe.is_opcua {
return findings;
}
let target = format!("{host}:{port}");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-opcua-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"OPC UA server exposed on the network".to_string(),
format!(
"An OPC UA server answers at {target}. Verify it enforces message security \
(a SecurityPolicy other than None) and rejects anonymous sessions — the common \
default of SecurityPolicy None + an Anonymous user token allows unauthenticated, \
unencrypted read/write of the server's address space."
),
Severity::Medium,
);
f.rule_id = Some("ics-opcua-exposed".to_string());
f.cwe = Some("CWE-319".to_string());
f.remediation = Some(
"Restrict OPC UA (4840) to a trusted network; require a signed & encrypted \
SecurityPolicy (Basic256Sha256 or better) with certificate / username \
authentication, and disable the Anonymous user token."
.to_string(),
);
findings.push(f);
findings
}
/// Findings from probing the EtherNet/IP (CIP) surface (default port 44818).
async fn enip_findings(host: &str, port: u16, repo_id: &str, budget: Duration) -> Vec<Finding> {
let probe = ethernetip::probe(host, port, budget).await;
if !probe.is_enip {
return Vec::new();
}
let target = format!("{host}:{port}");
let fp = dedup::compute_fingerprint(&[repo_id, "ics-ethernetip-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"EtherNet/IP (CIP) interface exposed on the network".to_string(),
format!(
"The device at {target} answers EtherNet/IP (CIP) requests. EtherNet/IP has no \
authentication in the base protocol, so a host that can reach it can enumerate \
and interact with the device's control objects."
),
Severity::High,
);
f.rule_id = Some("ics-ethernetip-exposed".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Restrict EtherNet/IP (44818/2222) to a trusted control network; use CIP Security \
(encryption + authentication) on devices that support it."
.to_string(),
);
vec![f]
}
/// Findings from the service-discovery port scan of the remaining OT /
/// insecure-management surface.
async fn portscan_findings(host: &str, repo_id: &str, budget: Duration) -> Vec<Finding> {
let open = portscan::scan(host, portscan::KNOWN_PORTS, budget).await;
open.into_iter()
.map(|kp| {
let target = format!("{host}:{}", kp.port);
let (title, severity, cwe, description) = match kp.kind {
portscan::PortKind::Ics => (
format!("ICS service exposed: {}", kp.service),
Severity::High,
"CWE-306",
format!(
"{target} exposes {} ({}). Industrial protocols are typically \
unauthenticated, so network reach implies control access.",
kp.service, kp.note
),
),
portscan::PortKind::InsecureMgmt => (
format!("Cleartext service exposed: {}", kp.service),
Severity::Medium,
"CWE-319",
format!(
"{target} exposes {} ({}), which transmits credentials and data in \
cleartext.",
kp.service, kp.note
),
),
};
let fp = dedup::compute_fingerprint(&[repo_id, "ics-service-exposed", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
title,
description,
severity,
);
f.rule_id = Some("ics-service-exposed".to_string());
f.cwe = Some(cwe.to_string());
f.remediation = Some(
"Restrict the service to a trusted network segment; disable it if unused; \
replace cleartext protocols (Telnet/FTP) with SSH/SFTP."
.to_string(),
);
f
})
.collect()
}
/// Extract `(host, port)` from a target reference. Modbus lives on its own port
/// (502 by default), independent of any HTTP/WebVisu URL, so unless the reference
/// explicitly carries `modbus://host:port` or a bare `host:port`, we probe 502.
fn parse_endpoint(endpoint: &str) -> (String, u16) {
let s = endpoint.trim();
let (scheme, rest) = match s.split_once("://") {
Some((sch, r)) => (Some(sch.to_ascii_lowercase()), r),
None => (None, s),
};
let hostport = rest.split(['/', '?']).next().unwrap_or(rest);
let (host, port) = match hostport.rsplit_once(':') {
Some((h, p)) => (h.to_string(), p.parse::<u16>().ok()),
None => (hostport.to_string(), None),
};
let port = match (scheme.as_deref(), port) {
// Explicit Modbus port, or a bare host:port the user chose.
(Some("modbus"), Some(p)) | (None, Some(p)) => p,
// An http(s)/WebVisu URL (or no port): Modbus is on its own port.
_ => MODBUS_PORT,
};
(host, port)
}
#[cfg(test)]
mod tests {
use super::parse_endpoint;
#[test]
fn endpoint_parsing_picks_the_modbus_port() {
assert_eq!(parse_endpoint("10.0.0.5"), ("10.0.0.5".into(), 502));
assert_eq!(parse_endpoint("10.0.0.5:1502"), ("10.0.0.5".into(), 1502));
assert_eq!(
parse_endpoint("modbus://plc.local:5020"),
("plc.local".into(), 5020)
);
// A WebVisu URL: the http port is ignored; Modbus is on 502.
assert_eq!(
parse_endpoint("http://plc.local:8080/webvisu"),
("plc.local".into(), 502)
);
assert_eq!(
parse_endpoint("https://plc.local/"),
("plc.local".into(), 502)
);
}
}
-205
View File
@@ -1,205 +0,0 @@
//! Minimal Modbus/TCP client for dynamic ICS probing.
//!
//! Modbus/TCP (port 502) has no authentication or encryption in the protocol, so
//! an endpoint that answers requests is, by design, open to any host that can
//! reach it. The probe only *reads* — a Read Holding Registers request and a Read
//! Device Identification request — and never writes to the live process.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of probing a Modbus/TCP endpoint.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct ModbusProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint answered a Modbus request (a normal reply or a Modbus
/// exception) — i.e. it speaks Modbus, unauthenticated.
pub speaks_modbus: bool,
/// Device identity, if disclosed via Read Device Identification (FC 43 / 14).
pub device: Option<DeviceId>,
}
/// Vendor / product / revision from Read Device Identification.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct DeviceId {
pub vendor: Option<String>,
pub product: Option<String>,
pub revision: Option<String>,
}
/// Probe a Modbus/TCP endpoint. Read-only: issues a Read Holding Registers and a
/// Read Device Identification request; never writes to the device.
pub async fn probe(host: &str, port: u16, budget: Duration) -> ModbusProbe {
let mut out = ModbusProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out; // unreachable
};
out.reachable = true;
// Read Holding Registers (FC 0x03), unit 1, addr 0, qty 1 — a benign read.
let rhr = [0x03u8, 0x00, 0x00, 0x00, 0x01];
if let Some(resp) = txn(&mut stream, 1, &rhr, budget).await {
// A normal reply (0x03) or an exception (0x83) both prove it speaks Modbus.
if matches!(resp.first(), Some(0x03) | Some(0x83)) {
out.speaks_modbus = true;
}
}
// Read Device Identification (FC 0x2B / MEI 0x0E), basic (0x01), object 0.
let rdi = [0x2Bu8, 0x0E, 0x01, 0x00];
if let Some(resp) = txn(&mut stream, 1, &rdi, budget).await {
if resp.first() == Some(&0x2B) {
out.speaks_modbus = true;
out.device = parse_device_id(&resp);
}
}
out
}
/// Send one Modbus PDU and return the response PDU (function code + data), or
/// `None` on timeout / malformed reply.
async fn txn(stream: &mut TcpStream, unit: u8, pdu: &[u8], budget: Duration) -> Option<Vec<u8>> {
// MBAP header: transaction id (2) + protocol id (2) = 0 + length (2) + unit (1),
// then the PDU. `length` counts the unit byte plus the PDU.
let len = (pdu.len() + 1) as u16;
let mut frame = Vec::with_capacity(7 + pdu.len());
frame.extend_from_slice(&[0x00, 0x01]); // transaction id
frame.extend_from_slice(&[0x00, 0x00]); // protocol id
frame.extend_from_slice(&len.to_be_bytes());
frame.push(unit);
frame.extend_from_slice(pdu);
timeout(budget, stream.write_all(&frame)).await.ok()?.ok()?;
let mut hdr = [0u8; 7];
timeout(budget, stream.read_exact(&mut hdr))
.await
.ok()?
.ok()?;
// Reject non-Modbus replies (protocol id must be 0).
if hdr[2] != 0 || hdr[3] != 0 {
return None;
}
let plen = u16::from_be_bytes([hdr[4], hdr[5]]) as usize;
if !(2..=260).contains(&plen) {
return None;
}
let mut body = vec![0u8; plen - 1]; // minus the unit id already in hdr[6]
timeout(budget, stream.read_exact(&mut body))
.await
.ok()?
.ok()?;
Some(body)
}
/// Parse vendor / product / revision from a Read Device Identification PDU:
/// `[0x2B, 0x0E, readDevIdCode, conformity, moreFollows, nextObjId, numObjects,
/// (objId, len, bytes…)…]`.
fn parse_device_id(pdu: &[u8]) -> Option<DeviceId> {
if pdu.len() < 7 {
return None;
}
let num = pdu[6] as usize;
let mut i = 7;
let mut dev = DeviceId::default();
for _ in 0..num {
if i + 2 > pdu.len() {
break;
}
let id = pdu[i];
let l = pdu[i + 1] as usize;
i += 2;
if i + l > pdu.len() {
break;
}
let val = String::from_utf8_lossy(&pdu[i..i + l]).trim().to_string();
i += l;
match id {
0x00 => dev.vendor = Some(val),
0x01 => dev.product = Some(val),
0x02 => dev.revision = Some(val),
_ => {}
}
}
if dev == DeviceId::default() {
None
} else {
Some(dev)
}
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
/// A one-shot mock Modbus/TCP server that answers a Read Holding Registers
/// request and a Read Device Identification request on one connection.
async fn mock_server(with_device: bool) -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
loop {
let mut hdr = [0u8; 7];
if sock.read_exact(&mut hdr).await.is_err() {
break;
}
let plen = u16::from_be_bytes([hdr[4], hdr[5]]) as usize;
let mut pdu = vec![0u8; plen - 1];
if sock.read_exact(&mut pdu).await.is_err() {
break;
}
let reply_pdu: Vec<u8> = match pdu.first() {
Some(0x03) => vec![0x03, 0x02, 0x00, 0x00], // 1 register = 0
Some(0x2B) if with_device => vec![
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x02, // 2 objects
0x00, 0x04, b'A', b'C', b'M', b'E', // vendor
0x01, 0x03, b'P', b'L', b'C', // product
],
_ => vec![pdu[0] | 0x80, 0x01], // exception
};
let len = (reply_pdu.len() + 1) as u16;
let mut frame = vec![hdr[0], hdr[1], 0x00, 0x00];
frame.extend_from_slice(&len.to_be_bytes());
frame.push(hdr[6]);
frame.extend_from_slice(&reply_pdu);
if sock.write_all(&frame).await.is_err() {
break;
}
}
});
addr
}
#[tokio::test]
async fn probe_detects_a_modbus_endpoint_and_reads_device_id() {
let addr = mock_server(true).await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.speaks_modbus);
let dev = p.device.expect("device id");
assert_eq!(dev.vendor.as_deref(), Some("ACME"));
assert_eq!(dev.product.as_deref(), Some("PLC"));
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
// 127.0.0.1:1 is (almost certainly) closed.
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.speaks_modbus);
}
#[test]
fn parses_device_identification_objects() {
let pdu = [
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x01, // 1 object
0x02, 0x05, b'v', b'1', b'.', b'2', b'3', // revision
];
let dev = parse_device_id(&pdu).expect("device");
assert_eq!(dev.revision.as_deref(), Some("v1.23"));
assert!(dev.vendor.is_none());
}
}
-131
View File
@@ -1,131 +0,0 @@
//! Minimal OPC UA reachability probe.
//!
//! Speaks just the OPC UA Connection Protocol (UACP) handshake — a `HEL` (Hello)
//! message, expecting an `ACK` (or `ERR`) reply — to confirm an OPC UA server is
//! listening (default port 4840). It does **not** open a secure channel or make
//! service calls; deep analysis of the server's SecurityPolicy / user-token
//! policies (the common `None` + `Anonymous` misconfiguration) is a follow-on best
//! done with a full OPC UA stack.
use std::time::Duration;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Outcome of an OPC UA handshake probe.
#[derive(Debug, Default, PartialEq, Eq)]
pub struct OpcUaProbe {
/// A TCP connection to the port was established.
pub reachable: bool,
/// The endpoint replied to the UACP Hello (`ACK`) or rejected it (`ERR`) —
/// either way it speaks OPC UA.
pub is_opcua: bool,
}
/// Probe an OPC UA endpoint with a UACP Hello. Read-only handshake only.
pub async fn probe(host: &str, port: u16, budget: Duration) -> OpcUaProbe {
let mut out = OpcUaProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
return out;
};
out.reachable = true;
let hello = hello_message(&format!("opc.tcp://{host}:{port}"));
if timeout(budget, stream.write_all(&hello))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
// Read the 3-byte message type of the reply: ACK (accepted) or ERR (rejected
// our hello) both prove the peer speaks the OPC UA connection protocol.
let mut mt = [0u8; 3];
if timeout(budget, stream.read_exact(&mut mt))
.await
.ok()
.and_then(Result::ok)
.is_none()
{
return out;
}
if &mt == b"ACK" || &mt == b"ERR" {
out.is_opcua = true;
}
out
}
/// Build a UACP `HEL` (Hello) message advertising our buffer sizes + endpoint URL.
fn hello_message(endpoint_url: &str) -> Vec<u8> {
let url = endpoint_url.as_bytes();
let mut m = Vec::with_capacity(32 + url.len());
m.extend_from_slice(b"HELF");
m.extend_from_slice(&0u32.to_le_bytes()); // message size — patched below
m.extend_from_slice(&0u32.to_le_bytes()); // ProtocolVersion
m.extend_from_slice(&65536u32.to_le_bytes()); // ReceiveBufferSize
m.extend_from_slice(&65536u32.to_le_bytes()); // SendBufferSize
m.extend_from_slice(&0u32.to_le_bytes()); // MaxMessageSize (0 = no limit)
m.extend_from_slice(&0u32.to_le_bytes()); // MaxChunkCount
m.extend_from_slice(&(url.len() as i32).to_le_bytes()); // EndpointUrl length
m.extend_from_slice(url);
let size = m.len() as u32;
m[4..8].copy_from_slice(&size.to_le_bytes());
m
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
/// A mock OPC UA server that reads the Hello and replies with an `ACK` frame.
async fn mock_server() -> std::net::SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let addr = listener.local_addr().expect("addr");
tokio::spawn(async move {
let (mut sock, _) = listener.accept().await.expect("accept");
// Read the Hello header (8 bytes) to learn the size, then drain it.
let mut hdr = [0u8; 8];
if sock.read_exact(&mut hdr).await.is_err() {
return;
}
let size = u32::from_le_bytes([hdr[4], hdr[5], hdr[6], hdr[7]]) as usize;
let mut rest = vec![0u8; size.saturating_sub(8)];
let _ = sock.read_exact(&mut rest).await;
// Reply: ACK + size + 5 u32 fields.
let mut ack = Vec::new();
ack.extend_from_slice(b"ACKF");
ack.extend_from_slice(&28u32.to_le_bytes());
for _ in 0..5 {
ack.extend_from_slice(&0u32.to_le_bytes());
}
let _ = sock.write_all(&ack).await;
});
addr
}
#[tokio::test]
async fn probe_detects_an_opcua_server() {
let addr = mock_server().await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.reachable && p.is_opcua);
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
let p = probe("127.0.0.1", 1, Duration::from_millis(500)).await;
assert!(!p.reachable && !p.is_opcua);
}
#[test]
fn hello_message_is_well_formed() {
let m = hello_message("opc.tcp://h:4840");
assert_eq!(&m[0..4], b"HELF");
// The embedded size equals the actual length.
let size = u32::from_le_bytes([m[4], m[5], m[6], m[7]]) as usize;
assert_eq!(size, m.len());
}
}
@@ -1,137 +0,0 @@
//! TCP service discovery for a device.
//!
//! Connect-scans a curated set of OT/ICS and insecure-management ports and reports
//! the ones that are open. The deep protocol probes own Modbus (502), OPC UA
//! (4840) and EtherNet/IP (44818); this surfaces the *rest* of the industrial and
//! cleartext-management surface (Siemens S7, DNP3, CODESYS programming, Telnet, …).
use std::time::Duration;
use futures_util::future::join_all;
use tokio::net::TcpStream;
use tokio::time::timeout;
/// Whether an open port is an industrial protocol or an insecure management service.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PortKind {
/// An industrial control protocol (typically unauthenticated).
Ics,
/// A cleartext management service (credentials/data in the clear).
InsecureMgmt,
}
/// A well-known port worth flagging when open.
#[derive(Debug, Clone, Copy)]
pub struct KnownPort {
pub port: u16,
pub service: &'static str,
pub kind: PortKind,
pub note: &'static str,
}
/// The curated scan list. Excludes 502 / 4840 / 44818 — those have dedicated deep
/// probes (Modbus, OPC UA, EtherNet/IP) that report richer findings.
pub const KNOWN_PORTS: &[KnownPort] = &[
KnownPort {
port: 102,
service: "S7comm / ISO-TSAP",
kind: PortKind::Ics,
note: "Siemens S7 PLC communication",
},
KnownPort {
port: 20000,
service: "DNP3",
kind: PortKind::Ics,
note: "SCADA / DNP3",
},
KnownPort {
port: 1911,
service: "Niagara Fox",
kind: PortKind::Ics,
note: "Tridium Niagara building automation",
},
KnownPort {
port: 11740,
service: "CODESYS",
kind: PortKind::Ics,
note: "CODESYS programming protocol",
},
KnownPort {
port: 1962,
service: "PCWorx",
kind: PortKind::Ics,
note: "Phoenix Contact PCWorx",
},
KnownPort {
port: 9600,
service: "OMRON FINS",
kind: PortKind::Ics,
note: "Omron FINS",
},
KnownPort {
port: 789,
service: "Red Lion Crimson",
kind: PortKind::Ics,
note: "Red Lion controllers",
},
KnownPort {
port: 23,
service: "Telnet",
kind: PortKind::InsecureMgmt,
note: "cleartext remote shell",
},
KnownPort {
port: 21,
service: "FTP",
kind: PortKind::InsecureMgmt,
note: "cleartext file transfer",
},
];
/// Connect-scan `ports` on `host` (concurrently) and return those that accept a
/// TCP connection.
pub async fn scan<'a>(host: &str, ports: &'a [KnownPort], budget: Duration) -> Vec<&'a KnownPort> {
let checks = ports.iter().map(|kp| async move {
let open = timeout(budget, TcpStream::connect((host, kp.port)))
.await
.map(|r| r.is_ok())
.unwrap_or(false);
(kp, open)
});
join_all(checks)
.await
.into_iter()
.filter_map(|(kp, open)| open.then_some(kp))
.collect()
}
#[cfg(test)]
mod tests {
use super::*;
use tokio::net::TcpListener;
#[tokio::test]
async fn scan_reports_only_open_ports() {
// Bind one port (open) and pick another that is closed.
let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
let open_port = listener.local_addr().expect("addr").port();
let ports = [
KnownPort {
port: open_port,
service: "test-open",
kind: PortKind::Ics,
note: "",
},
KnownPort {
port: 1,
service: "test-closed",
kind: PortKind::InsecureMgmt,
note: "",
},
];
let found = scan("127.0.0.1", &ports, Duration::from_millis(500)).await;
let services: Vec<&str> = found.iter().map(|p| p.service).collect();
assert_eq!(services, vec!["test-open"]);
}
}
-2
View File
@@ -5,13 +5,11 @@ pub mod firmware_sbom;
pub mod git;
pub mod gitleaks;
mod graph_build;
pub mod ics;
mod issue_creation;
pub mod lint;
pub mod orchestrator;
pub mod patterns;
pub mod plan;
pub mod plc;
mod pr_review;
pub mod repo_view;
pub mod sbom;
+67 -313
View File
@@ -259,13 +259,68 @@ impl PipelineOrchestrator {
.await?;
}
// Persist CVE alerts and create notifications (shared with the PLC path).
let new_notif_count = self
.persist_cve_alerts(&repo_id, &repo.name, &cve_alerts)
// Persist CVE alerts and create notifications
{
use compliance_core::models::notification::{parse_severity, CveNotification};
let repo_name = repo.name.clone();
let mut new_notif_count = 0u32;
for alert in &cve_alerts {
// Upsert the alert
let filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
};
let update = mongodb::bson::to_document(alert)
.map(|d| doc! { "$set": d })
.unwrap_or_else(|_| doc! {});
self.db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
.await?;
// Create notification (dedup by cve_id + repo + package + version)
let notif_filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
"package_name": &alert.affected_package,
"package_version": &alert.affected_version,
};
let severity = parse_severity(alert.severity.as_deref(), alert.cvss_score);
let mut notification = CveNotification::new(
alert.cve_id.clone(),
repo_id.clone(),
repo_name.clone(),
alert.affected_package.clone(),
alert.affected_version.clone(),
severity,
);
notification.cvss_score = alert.cvss_score;
notification.summary = alert.summary.clone();
notification.url = Some(format!("https://osv.dev/vulnerability/{}", alert.cve_id));
let notif_update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
if let Ok(result) = self
.db
.cve_notifications()
.update_one(notif_filter, notif_update)
.upsert(true)
.await
{
if result.upserted_id.is_some() {
new_notif_count += 1;
}
}
}
if new_notif_count > 0 {
tracing::info!("[{repo_id}] Created {new_notif_count} CVE notification(s)");
}
}
// Stage 6: Issue Creation
tracing::info!("[{repo_id}] Stage 6: Issue Creation");
@@ -394,334 +449,33 @@ impl PipelineOrchestrator {
// wizard-created targets, not just migrated ones.
self.ensure_dast_target(target, &plan).await;
// PLC/SPS targets: the control-logic scan consumes the PLC source (an
// uploaded PlcProject *or* a git repo / source archive of PLCopen XML / ST
// exports), so it takes over the code artifact — we don't also run the
// SAST pipeline over it. A PLC device is reachable, so DAST still runs
// against a WebVisu / exposed endpoint when one is provisioned.
let mut new_count = 0u32;
let plc = plan.has(ScanType::PlcControlLogic);
let ics = plan.has(ScanType::IcsProbe);
if plc {
new_count += self.run_plc_scan(target, &target_id, scan_run_id).await?;
}
if ics {
new_count += self.run_ics_probe(target, &target_id, scan_run_id).await?;
}
if plc || ics {
// PLC/SPS device: also DAST against a WebVisu / exposed endpoint, but
// only when DAST is actually planned — a device reachable only over an
// industrial protocol (e.g. modbus://) has no web surface to crawl, and
// running DAST there just fails at reconnaissance. Gating here (not only
// at provisioning) also stops a DAST target left over from an earlier
// run from re-triggering. The control-logic scan already consumed the
// code artifact, so the SAST pipeline is not re-run.
if plan.has(ScanType::Dast) {
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
}
return Ok(new_count);
}
match target.code_artifact() {
Some(code) if code.kind == ArtifactKind::GitRepo => {
let repo = RepoView::from_target(target, code);
let n = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, n).await?;
new_count += n;
let new_count = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, new_count).await?;
Ok(new_count)
}
Some(_) => {
tracing::warn!(
target_id = %target_id,
"Unified pipeline: source-archive scanning not yet wired; skipping"
);
Ok(0)
}
None => {
// No code to scan (a migrated DAST target). Firmware/mobile static
// scanners land in #128/#129; DAST for a running URL works when a
// DastTarget row exists (provisioned above from a LiveUrl, or from
// a migrated target).
// No code to scan. Firmware/PLC/mobile static scanners land in
// #128/#129/#130; DAST for a running URL still works when a
// DastTarget row exists (migrated targets).
tracing::info!(
target_id = %target_id,
"Unified pipeline: no code artifact; attempting DAST"
"Unified pipeline: no code artifact; attempting DAST only"
);
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
Ok(0)
}
}
Ok(new_count)
}
/// Analyze a PLC/SPS project (Structured Text / PLCopen XML) for
/// control-logic security issues and persist the new findings.
async fn run_plc_scan(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
tracing::info!(target_id, "[{target_id}] PLC control-logic analysis");
self.update_phase(scan_run_id, "plc_analysis").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = crate::ingest::ingest_all(target, &ctx)?;
// Every PLC-source artifact on the target: dedicated PLC projects plus any
// code artifacts (git repo / source archive) holding PLCopen XML / ST
// exports. A target can carry several (e.g. one POU export per file).
let sources: Vec<&Artifact> = target
.artifacts
.iter()
.filter(|a| {
matches!(
a.kind,
ArtifactKind::PlcProject | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
)
})
.collect();
if sources.is_empty() {
tracing::warn!(target_id, "PLC scan: no PLC source artifact");
return Ok(0);
}
let mut all_findings = Vec::new();
let mut all_sbom: Vec<SbomEntry> = Vec::new();
let mut sbom_seen = std::collections::BTreeSet::new();
for a in &sources {
let Some(path) = ingest_set.get(&a.id).and_then(|ia| ia.working_path.clone()) else {
continue;
};
all_findings.extend(crate::pipeline::plc::analyze_tree(&path, target_id));
// Control-application SBOM: CODESYS libraries + runtime from a
// `.projectarchive` (uploaded, or committed in the working tree).
let archive = a
.stored_path
.clone()
.unwrap_or_else(|| a.source_ref.clone());
for e in crate::pipeline::plc::sbom::collect_sbom(
std::path::Path::new(&archive),
&path,
target_id,
) {
if sbom_seen.insert((e.name.clone(), e.version.clone())) {
all_sbom.push(e);
}
}
}
tracing::info!(
target_id,
artifacts = sources.len(),
found = all_findings.len(),
"PLC control-logic analysis complete"
);
let mut new_count = 0u32;
for mut finding in all_findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
if !all_sbom.is_empty() {
if let Err(e) = self
.persist_control_app_sbom(target_id, &target.name, all_sbom)
.await
{
tracing::warn!(target_id, error = %e, "control-app SBOM persist failed");
}
}
Ok(new_count)
}
/// Probe a running PLC/SPS device over industrial protocols (Modbus/TCP, …)
/// and persist findings for exposed / unauthenticated control access. The
/// probe is read-only; it targets the Modbus port of the target's live URL.
async fn run_ics_probe(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
self.update_phase(scan_run_id, "ics_probe").await;
let Some(endpoint) = target.live_url().map(|a| a.source_ref.clone()) else {
tracing::warn!(target_id, "ICS probe: no live URL");
return Ok(0);
};
// Short per-request budget so an unreachable device doesn't stall the scan.
let budget = std::time::Duration::from_secs(5);
let findings = crate::pipeline::ics::probe_target(&endpoint, target_id, budget).await;
tracing::info!(
target_id,
endpoint = %endpoint,
found = findings.len(),
"ICS probe complete"
);
let mut new_count = 0u32;
for mut finding in findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
Ok(new_count)
}
/// Store a control-application SBOM (CODESYS libraries + runtime) for a target
/// and match it against known CVEs. Scoped to `package_manager = "codesys"` so
/// it refreshes on re-scan and coexists with any firmware/source SBOM. The
/// runtime `Cmp*` / `3SLicense` components carry real CODESYS advisories, so
/// this is where PLC-device CVE coverage comes from.
async fn persist_control_app_sbom(
&self,
target_id: &str,
target_name: &str,
mut entries: Vec<SbomEntry>,
) -> Result<(), AgentError> {
if entries.is_empty() {
return Ok(());
}
self.db
.sbom_entries()
.delete_many(doc! { "repo_id": target_id, "package_manager": "codesys" })
.await?;
let cve_scanner = CveScanner::new(
self.http.clone(),
self.config.searxng_url.clone(),
self.config.nvd_api_key.as_ref().map(|k| {
use secrecy::ExposeSecret;
k.expose_secret().to_string()
}),
);
let mut alerts = match tokio::time::timeout(
std::time::Duration::from_secs(600),
cve_scanner.scan_dependencies(target_id, &mut entries),
)
.await
{
Ok(Ok(a)) => a,
Ok(Err(e)) => {
tracing::warn!(target_id, error = %e, "control-app CVE scan failed");
Vec::new()
}
Err(_) => {
tracing::warn!(target_id, "control-app CVE scan timed out");
Vec::new()
}
};
// OSV can't match `pkg:codesys/*` (no such ecosystem); CODESYS advisories
// live in NVD keyed by CPE + runtime version. Add those (best-effort).
if let Ok(codesys) = tokio::time::timeout(
std::time::Duration::from_secs(120),
cve_scanner.scan_codesys(target_id, &mut entries),
)
.await
{
alerts.extend(codesys);
} else {
tracing::warn!(target_id, "CODESYS CVE match timed out");
}
for entry in &entries {
let filter = doc! {
"repo_id": &entry.repo_id,
"name": &entry.name,
"version": &entry.version,
};
if let Ok(d) = mongodb::bson::to_document(entry) {
self.db
.sbom_entries()
.update_one(filter, doc! { "$set": d })
.upsert(true)
.await?;
}
}
let new_notifs = self
.persist_cve_alerts(target_id, target_name, &alerts)
.await?;
tracing::info!(
target_id,
components = entries.len(),
alerts = alerts.len(),
notifications = new_notifs,
"control-app SBOM stored"
);
Ok(())
}
/// Upsert CVE alerts for a target and create dedup'd CVE notifications;
/// returns the number of newly-created notifications. Shared by the SAST
/// pipeline and the PLC control-app SBOM path, so every SBOM source (source,
/// firmware, CODESYS libraries/runtime) raises the same notifications.
async fn persist_cve_alerts(
&self,
repo_id: &str,
repo_name: &str,
alerts: &[CveAlert],
) -> Result<u32, AgentError> {
use compliance_core::models::notification::{parse_severity, CveNotification};
let mut new_notif = 0u32;
for alert in alerts {
let filter = doc! { "cve_id": &alert.cve_id, "repo_id": &alert.repo_id };
let update = mongodb::bson::to_document(alert)
.map(|d| doc! { "$set": d })
.unwrap_or_else(|_| doc! {});
self.db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
.await?;
// Dedup notifications by cve + repo + package + version.
let notif_filter = doc! {
"cve_id": &alert.cve_id,
"repo_id": &alert.repo_id,
"package_name": &alert.affected_package,
"package_version": &alert.affected_version,
};
let severity = parse_severity(alert.severity.as_deref(), alert.cvss_score);
let mut notification = CveNotification::new(
alert.cve_id.clone(),
repo_id.to_string(),
repo_name.to_string(),
alert.affected_package.clone(),
alert.affected_version.clone(),
severity,
);
notification.cvss_score = alert.cvss_score;
notification.summary = alert.summary.clone();
notification.url = Some(format!("https://osv.dev/vulnerability/{}", alert.cve_id));
let notif_update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
if let Ok(result) = self
.db
.cve_notifications()
.update_one(notif_filter, notif_update)
.upsert(true)
.await
{
if result.upserted_id.is_some() {
new_notif += 1;
}
}
}
Ok(new_notif)
}
/// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto,
+1 -20
View File
@@ -75,16 +75,10 @@ pub fn build_scan_plan(target: &OnboardedTarget) -> ScanPlan {
}
/// Resolve the artifact a scan consumes. A "code" requirement (represented by
/// `GitRepo`) is satisfied by a git repo *or* a source archive. The PLC
/// control-logic requirement (represented by `PlcProject`) prefers an uploaded
/// PLC project but also accepts a code artifact — a git repo / source archive
/// holding PLCopen XML / ST exports.
/// `GitRepo`) is satisfied by a git repo *or* a source archive.
fn resolve_artifact(target: &OnboardedTarget, required: Option<ArtifactKind>) -> Option<&Artifact> {
match required {
Some(ArtifactKind::GitRepo) => target.code_artifact(),
Some(ArtifactKind::PlcProject) => target
.first_of(ArtifactKind::PlcProject)
.or_else(|| target.code_artifact()),
Some(kind) => target.first_of(kind),
None => target.code_artifact().or_else(|| target.artifacts.first()),
}
@@ -106,7 +100,6 @@ fn phase_for(scan: ScanType) -> ScanPhase {
ScanType::PlcControlLogic => ScanPhase::PlcAnalysis,
ScanType::MobileStatic => ScanPhase::MobileStatic,
ScanType::ContainerScan => ScanPhase::ContainerScan,
ScanType::IcsProbe => ScanPhase::IcsProbe,
}
}
@@ -181,18 +174,6 @@ mod tests {
assert_eq!(plan.steps[0].phase, ScanPhase::PlcAnalysis);
}
#[test]
fn plc_control_logic_binds_to_a_git_repo() {
// A CODESYS project in git (PLCopen XML / ST exports) with no uploaded
// PlcProject: control-logic still plans, bound to the git artifact.
let git = Artifact::git_repo("https://git/plc", "main");
let git_id = git.id.clone();
let t = target(TargetType::PlcSps, vec![git]);
let plan = build_scan_plan(&t);
let step = step_for(&plan, ScanType::PlcControlLogic).expect("control-logic planned");
assert_eq!(step.artifact_id, git_id, "PLC scan binds to the git repo");
}
#[test]
fn disabled_scan_is_dropped_and_off_by_default_can_be_enabled() {
let mut t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
-226
View File
@@ -1,226 +0,0 @@
//! Abstract syntax tree for IEC 61131-3 Structured Text (ST).
//!
//! This is the security-relevant subset: POUs with their variable declarations
//! and statement bodies, enough to run semantic control-logic rules over. It is
//! deliberately not a full language model — declarations we don't reason about
//! (e.g. exotic type definitions) are parsed loosely and kept as raw text.
/// A Program Organization Unit: a PROGRAM, FUNCTION, or FUNCTION_BLOCK.
#[derive(Debug, Clone)]
pub struct Pou {
pub name: String,
pub kind: PouKind,
/// The declared variables, across all VAR_* sections.
pub vars: Vec<VarDecl>,
/// The statement body.
pub body: Vec<Stmt>,
/// 1-based line where the POU header appears (in the source that was parsed).
pub line: u32,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PouKind {
Program,
Function,
FunctionBlock,
}
impl PouKind {
pub fn label(self) -> &'static str {
match self {
PouKind::Program => "PROGRAM",
PouKind::Function => "FUNCTION",
PouKind::FunctionBlock => "FUNCTION_BLOCK",
}
}
}
/// A single declared variable.
#[derive(Debug, Clone)]
pub struct VarDecl {
pub name: String,
pub section: VarSection,
/// The declared type as written (e.g. `BOOL`, `INT`, `ARRAY[0..9] OF INT`).
pub type_name: String,
/// Whether the type is an ARRAY, and its declared bounds `(lo, hi)` when
/// they are literal integers — used by the array-bounds rule.
pub array_bounds: Option<(i64, i64)>,
/// The initializer expression, if any (`:= <expr>`).
pub init: Option<Expr>,
pub line: u32,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum VarSection {
Var,
Input,
Output,
InOut,
Global,
Temp,
External,
}
/// A statement.
#[derive(Debug, Clone)]
pub enum Stmt {
Assign {
target: Expr,
value: Expr,
line: u32,
},
If {
/// (condition, body) for IF and each ELSIF, in order.
branches: Vec<(Expr, Vec<Stmt>)>,
else_body: Option<Vec<Stmt>>,
line: u32,
},
Case {
selector: Expr,
/// (label expressions, body) per CASE arm.
arms: Vec<(Vec<Expr>, Vec<Stmt>)>,
else_body: Option<Vec<Stmt>>,
line: u32,
},
For {
var: String,
from: Expr,
to: Expr,
by: Option<Expr>,
body: Vec<Stmt>,
line: u32,
},
While {
cond: Expr,
body: Vec<Stmt>,
line: u32,
},
Repeat {
body: Vec<Stmt>,
until: Expr,
line: u32,
},
/// A bare call statement, e.g. `TON1(IN := x, PT := T#5s);`.
Call {
callee: String,
args: Vec<CallArg>,
line: u32,
},
Return {
line: u32,
},
Exit {
line: u32,
},
/// `JMP label;` — an unstructured jump.
Jump {
label: String,
line: u32,
},
/// `label:` — a jump target.
Label {
name: String,
line: u32,
},
}
/// One argument in a call: positional (`name: None`) or named (`X := expr`).
#[derive(Debug, Clone)]
pub struct CallArg {
pub name: Option<String>,
pub value: Expr,
}
/// An expression.
#[derive(Debug, Clone)]
pub enum Expr {
Int(i64, u32),
Real(f64, u32),
Bool(bool, u32),
/// A string literal, with the unquoted contents.
Str(String, u32),
/// A duration / date / time literal, kept as raw text (`T#5s`, `DT#...`).
Time(String, u32),
Ident(String, u32),
/// `base[index]`.
Index {
base: Box<Expr>,
index: Box<Expr>,
line: u32,
},
/// `base.field`.
Member {
base: Box<Expr>,
field: String,
line: u32,
},
Unary {
op: UnOp,
expr: Box<Expr>,
line: u32,
},
Binary {
op: BinOp,
lhs: Box<Expr>,
rhs: Box<Expr>,
line: u32,
},
/// A function call used as an expression, e.g. `LIMIT(a, b, c)`.
Call {
callee: String,
args: Vec<CallArg>,
line: u32,
},
}
impl Expr {
/// The 1-based source line this expression starts on.
pub fn line(&self) -> u32 {
match self {
Expr::Int(_, l)
| Expr::Real(_, l)
| Expr::Bool(_, l)
| Expr::Str(_, l)
| Expr::Time(_, l)
| Expr::Ident(_, l)
| Expr::Index { line: l, .. }
| Expr::Member { line: l, .. }
| Expr::Unary { line: l, .. }
| Expr::Binary { line: l, .. }
| Expr::Call { line: l, .. } => *l,
}
}
/// If this expression is a plain identifier, its name.
pub fn as_ident(&self) -> Option<&str> {
match self {
Expr::Ident(name, _) => Some(name.as_str()),
_ => None,
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum UnOp {
Not,
Neg,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum BinOp {
Add,
Sub,
Mul,
Div,
Mod,
Pow,
Eq,
Ne,
Lt,
Le,
Gt,
Ge,
And,
Or,
Xor,
}
-372
View File
@@ -1,372 +0,0 @@
//! Lexer for IEC 61131-3 Structured Text.
//!
//! Tokenizes ST source into a flat token stream with 1-based line numbers.
//! Keywords are case-insensitive. Handles `(* *)` and `//` comments, `'..'` and
//! `".."` strings (with `''`/`""` escapes), based integers (`16#FF`, `2#1010`),
//! and duration/date literals (`T#5s`, `DT#...`) kept as raw text.
/// A lexed token with its source line.
#[derive(Debug, Clone)]
pub struct Token {
pub kind: Tok,
pub line: u32,
}
#[derive(Debug, Clone, PartialEq)]
pub enum Tok {
Int(i64),
Real(f64),
Str(String),
Time(String),
Bool(bool),
Ident(String),
Kw(Keyword),
Assign, // :=
Plus, // +
Minus, // -
Star, // *
Slash, // /
Power, // **
LParen, // (
RParen, // )
LBrack, // [
RBrack, // ]
Dot, // .
DotDot, // ..
Comma, // ,
Semi, // ;
Colon, // :
Lt, // <
Le, // <=
Gt, // >
Ge, // >=
Eq, // =
Ne, // <>
Amp, // &
Eof,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum Keyword {
Program,
EndProgram,
Function,
EndFunction,
FunctionBlock,
EndFunctionBlock,
Var,
VarInput,
VarOutput,
VarInOut,
VarGlobal,
VarTemp,
VarExternal,
Constant,
EndVar,
Array,
Of,
If,
Then,
Elsif,
Else,
EndIf,
Case,
EndCase,
For,
To,
By,
Do,
EndFor,
While,
EndWhile,
Repeat,
Until,
EndRepeat,
Return,
Exit,
Jmp,
Not,
And,
Or,
Xor,
Mod,
Type,
EndType,
Struct,
EndStruct,
}
fn keyword_from(word: &str) -> Option<Keyword> {
use Keyword::*;
Some(match word.to_ascii_uppercase().as_str() {
"PROGRAM" => Program,
"END_PROGRAM" => EndProgram,
"FUNCTION" => Function,
"END_FUNCTION" => EndFunction,
"FUNCTION_BLOCK" => FunctionBlock,
"END_FUNCTION_BLOCK" => EndFunctionBlock,
"VAR" => Var,
"VAR_INPUT" => VarInput,
"VAR_OUTPUT" => VarOutput,
"VAR_IN_OUT" => VarInOut,
"VAR_GLOBAL" => VarGlobal,
"VAR_TEMP" => VarTemp,
"VAR_EXTERNAL" => VarExternal,
"CONSTANT" => Constant,
"END_VAR" => EndVar,
"ARRAY" => Array,
"OF" => Of,
"IF" => If,
"THEN" => Then,
"ELSIF" => Elsif,
"ELSE" => Else,
"END_IF" => EndIf,
"CASE" => Case,
"END_CASE" => EndCase,
"FOR" => For,
"TO" => To,
"BY" => By,
"DO" => Do,
"END_FOR" => EndFor,
"WHILE" => While,
"END_WHILE" => EndWhile,
"REPEAT" => Repeat,
"UNTIL" => Until,
"END_REPEAT" => EndRepeat,
"RETURN" => Return,
"EXIT" => Exit,
"JMP" => Jmp,
"NOT" => Not,
"AND" => And,
"OR" => Or,
"XOR" => Xor,
"MOD" => Mod,
"TYPE" => Type,
"END_TYPE" => EndType,
"STRUCT" => Struct,
"END_STRUCT" => EndStruct,
_ => return None,
})
}
/// Tokenize `src`. Unknown characters are skipped (best-effort — a scanner must
/// not die on odd input).
pub fn lex(src: &str) -> Vec<Token> {
let chars: Vec<char> = src.chars().collect();
let mut i = 0usize;
let mut line = 1u32;
let mut out = Vec::new();
let bump_line = |c: char, line: &mut u32| {
if c == '\n' {
*line += 1;
}
};
while i < chars.len() {
let c = chars[i];
// Whitespace.
if c.is_whitespace() {
bump_line(c, &mut line);
i += 1;
continue;
}
// Line comment: //
if c == '/' && i + 1 < chars.len() && chars[i + 1] == '/' {
while i < chars.len() && chars[i] != '\n' {
i += 1;
}
continue;
}
// Block comment: (* ... *)
if c == '(' && i + 1 < chars.len() && chars[i + 1] == '*' {
i += 2;
while i + 1 < chars.len() && !(chars[i] == '*' && chars[i + 1] == ')') {
bump_line(chars[i], &mut line);
i += 1;
}
i = (i + 2).min(chars.len());
continue;
}
let tok_line = line;
// String literal: '...' or "..."
if c == '\'' || c == '"' {
let quote = c;
i += 1;
let mut s = String::new();
while i < chars.len() {
let ch = chars[i];
if ch == quote {
// Doubled quote is an escaped quote.
if i + 1 < chars.len() && chars[i + 1] == quote {
s.push(quote);
i += 2;
continue;
}
i += 1;
break;
}
bump_line(ch, &mut line);
s.push(ch);
i += 1;
}
out.push(Token {
kind: Tok::Str(s),
line: tok_line,
});
continue;
}
// Identifier / keyword / time literal / boolean.
if c.is_ascii_alphabetic() || c == '_' {
let start = i;
while i < chars.len() && (chars[i].is_ascii_alphanumeric() || chars[i] == '_') {
i += 1;
}
let word: String = chars[start..i].iter().collect();
// Duration/date/time literal prefix: T#, TIME#, DT#, D#, TOD#, LT# ...
if i < chars.len() && chars[i] == '#' {
let up = word.to_ascii_uppercase();
if matches!(
up.as_str(),
"T" | "TIME" | "DT" | "D" | "TOD" | "LT" | "DATE"
) {
let lit_start = start;
i += 1; // consume '#'
while i < chars.len()
&& (chars[i].is_ascii_alphanumeric()
|| chars[i] == '.'
|| chars[i] == '_'
|| chars[i] == ':')
{
i += 1;
}
let lit: String = chars[lit_start..i].iter().collect();
out.push(Token {
kind: Tok::Time(lit),
line: tok_line,
});
continue;
}
}
let kind = match word.to_ascii_uppercase().as_str() {
"TRUE" => Tok::Bool(true),
"FALSE" => Tok::Bool(false),
_ => match keyword_from(&word) {
Some(kw) => Tok::Kw(kw),
None => Tok::Ident(word),
},
};
out.push(Token {
kind,
line: tok_line,
});
continue;
}
// Number: decimal, real, or based (16#..., 2#...).
if c.is_ascii_digit() {
let start = i;
while i < chars.len() && (chars[i].is_ascii_digit() || chars[i] == '_') {
i += 1;
}
// Based literal: <base>#<digits>
if i < chars.len() && chars[i] == '#' {
let base_str: String = chars[start..i].iter().filter(|c| **c != '_').collect();
i += 1;
let dstart = i;
while i < chars.len() && (chars[i].is_ascii_alphanumeric() || chars[i] == '_') {
i += 1;
}
let digits: String = chars[dstart..i].iter().filter(|c| **c != '_').collect();
let radix = base_str.parse::<u32>().unwrap_or(10);
let val = i64::from_str_radix(&digits, radix.clamp(2, 36)).unwrap_or(0);
out.push(Token {
kind: Tok::Int(val),
line: tok_line,
});
continue;
}
// Real: has a '.' (not '..') or exponent.
let is_real =
i < chars.len() && chars[i] == '.' && !(i + 1 < chars.len() && chars[i + 1] == '.');
if is_real {
i += 1;
while i < chars.len() && (chars[i].is_ascii_digit() || chars[i] == '_') {
i += 1;
}
let raw: String = chars[start..i].iter().filter(|c| **c != '_').collect();
out.push(Token {
kind: Tok::Real(raw.parse().unwrap_or(0.0)),
line: tok_line,
});
continue;
}
let raw: String = chars[start..i].iter().filter(|c| **c != '_').collect();
out.push(Token {
kind: Tok::Int(raw.parse().unwrap_or(0)),
line: tok_line,
});
continue;
}
// Operators / punctuation (longest match first).
let two: String = chars[i..(i + 2).min(chars.len())].iter().collect();
let kind = match two.as_str() {
":=" => Some(Tok::Assign),
"<=" => Some(Tok::Le),
">=" => Some(Tok::Ge),
"<>" => Some(Tok::Ne),
".." => Some(Tok::DotDot),
"**" => Some(Tok::Power),
_ => None,
};
if let Some(k) = kind {
out.push(Token {
kind: k,
line: tok_line,
});
i += 2;
continue;
}
let one = match c {
'+' => Some(Tok::Plus),
'-' => Some(Tok::Minus),
'*' => Some(Tok::Star),
'/' => Some(Tok::Slash),
'(' => Some(Tok::LParen),
')' => Some(Tok::RParen),
'[' => Some(Tok::LBrack),
']' => Some(Tok::RBrack),
'.' => Some(Tok::Dot),
',' => Some(Tok::Comma),
';' => Some(Tok::Semi),
':' => Some(Tok::Colon),
'<' => Some(Tok::Lt),
'>' => Some(Tok::Gt),
'=' => Some(Tok::Eq),
'&' => Some(Tok::Amp),
_ => None,
};
if let Some(k) = one {
out.push(Token {
kind: k,
line: tok_line,
});
}
i += 1;
}
out.push(Token {
kind: Tok::Eof,
line,
});
out
}
-234
View File
@@ -1,234 +0,0 @@
//! PLC control-logic security scanner for IEC 61131-3 targets.
//!
//! Parses Structured Text (raw `.st`/`.scl`/`.exp` files and PLCopen-XML
//! projects) into an AST and runs semantic control-logic security rules over it.
//! Implements [`ScanType::PlcControlLogic`].
pub mod ast;
pub mod lexer;
pub mod parser;
pub mod plcopen;
pub mod rules;
pub mod sbom;
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{Finding, ScanType};
use compliance_core::traits::{ScanOutput, Scanner};
use crate::pipeline::dedup;
/// Scanner for `ScanType::PlcControlLogic`.
pub struct PlcControlLogicScanner;
impl Scanner for PlcControlLogicScanner {
fn name(&self) -> &str {
"plc-control-logic"
}
fn scan_type(&self) -> ScanType {
ScanType::PlcControlLogic
}
#[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let findings = analyze_tree(repo_path, repo_id);
Ok(ScanOutput {
findings,
sbom_entries: Vec::new(),
})
}
}
/// Walk a PLC project tree and produce findings.
pub(crate) fn analyze_tree(root: &Path, repo_id: &str) -> Vec<Finding> {
let mut findings = Vec::new();
for entry in walkdir::WalkDir::new(root)
.into_iter()
.filter_map(|e| e.ok())
{
if !entry.file_type().is_file() {
continue;
}
let path = entry.path();
let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_ascii_lowercase();
let is_st = matches!(ext.as_str(), "st" | "iecst" | "scl" | "exp" | "il");
let is_xml = matches!(ext.as_str(), "xml" | "plcopen" | "project");
if !is_st && !is_xml {
continue;
}
let Ok(content) = std::fs::read_to_string(path) else {
continue;
};
let pous = if is_xml {
plcopen::parse_plcopen(&content)
} else {
parser::parse(&content)
};
if pous.is_empty() {
continue;
}
let rel = path
.strip_prefix(root)
.unwrap_or(path)
.to_string_lossy()
.to_string();
for pou in &pous {
for hit in rules::analyze(pou) {
let line_s = hit.line.to_string();
let fingerprint =
dedup::compute_fingerprint(&[repo_id, &rel, hit.rule_id, &pou.name, &line_s]);
let mut f = Finding::new(
repo_id.to_string(),
fingerprint,
"plc-control-logic".to_string(),
ScanType::PlcControlLogic,
hit.title,
hit.description,
hit.severity,
);
f.file_path = Some(rel.clone());
f.line_number = Some(hit.line);
f.rule_id = Some(hit.rule_id.to_string());
f.cwe = hit.cwe.map(String::from);
f.remediation = Some(hit.remediation.to_string());
findings.push(f);
}
}
}
findings
}
#[cfg(test)]
mod tests {
use super::*;
use std::collections::HashSet;
use std::path::PathBuf;
fn demo_dir() -> PathBuf {
PathBuf::from(env!("CARGO_MANIFEST_DIR"))
.parent()
.expect("workspace root")
.join("examples/plc-demo")
}
#[test]
fn scans_demo_project_end_to_end() {
let findings = analyze_tree(&demo_dir(), "demo-target");
assert!(!findings.is_empty(), "demo project should produce findings");
let rules: HashSet<&str> = findings
.iter()
.filter_map(|f| f.rule_id.as_deref())
.collect();
for r in [
"plc-hardcoded-credential",
"plc-default-password",
"plc-safety-bypass",
"plc-array-unchecked-index",
"plc-insecure-comm",
"plc-insecure-protocol-port",
"plc-unstructured-jump",
"plc-division-by-zero",
] {
assert!(rules.contains(r), "expected rule {r}; got {rules:?}");
}
// Every finding is well-formed for storage.
for f in &findings {
assert_eq!(f.repo_id, "demo-target");
assert!(f.file_path.is_some(), "finding needs a file");
assert!(f.line_number.is_some(), "finding needs a line");
}
// The guarded division (IF ScaleFactor <> 0.0) must not be double-counted:
// exactly one division-by-zero (the unguarded MeasuredFlow divide).
let div0 = findings
.iter()
.filter(|f| f.rule_id.as_deref() == Some("plc-division-by-zero"))
.count();
assert_eq!(div0, 1, "only the unguarded division should be flagged");
}
/// The realistic OpenPLC-style traffic-light sample is mostly sound control
/// logic: the scanner must surface its few genuine defects and stay quiet on
/// the timed state machine and the guarded duty-cycle division.
#[test]
fn realistic_sample_flags_only_real_issues() {
let all = analyze_tree(&demo_dir(), "demo-target");
let tl: Vec<_> = all
.iter()
.filter(|f| {
f.file_path
.as_deref()
.is_some_and(|p| p.ends_with("traffic_light.st"))
})
.collect();
assert!(!tl.is_empty(), "traffic_light.st should produce findings");
let rules: HashSet<&str> = tl.iter().filter_map(|f| f.rule_id.as_deref()).collect();
// The three planted defects: hardcoded SCADA password, cleartext Modbus
// master (no auth), and a maintenance mode that drops the PedPermit.
for r in [
"plc-hardcoded-credential",
"plc-insecure-comm",
"plc-safety-bypass",
] {
assert!(rules.contains(r), "expected rule {r}; got {rules:?}");
}
// Modbus/TCP on 502 is also an insecure-protocol port.
assert!(rules.contains("plc-insecure-protocol-port"));
// Low false positives: the guarded `IF LampCount <> 0` division and the
// JMP-free state machine must not trip anything.
assert_eq!(
tl.iter()
.filter(|f| f.rule_id.as_deref() == Some("plc-division-by-zero"))
.count(),
0,
"the guarded duty-cycle division must not be flagged"
);
assert!(
!rules.contains("plc-unstructured-jump"),
"the CASE state machine uses no JMP"
);
}
/// Graphical logic must be analysed too: an FBD POU (blocks + in/out
/// variables) is translated to synthetic ST, so the same rules fire on the
/// cleartext Modbus block, the hardcoded HMI password and the safety write.
#[test]
fn fbd_graphical_body_is_analysed() {
let all = analyze_tree(&demo_dir(), "demo-target");
let fbd: Vec<_> = all
.iter()
.filter(|f| {
f.file_path
.as_deref()
.is_some_and(|p| p.ends_with("pump_fbd.xml"))
})
.collect();
assert!(
!fbd.is_empty(),
"pump_fbd.xml (FBD) should produce findings"
);
let rules: HashSet<&str> = fbd.iter().filter_map(|f| f.rule_id.as_deref()).collect();
for r in [
"plc-insecure-comm", // Modbus_TCP_Master(AUTH := FALSE)
"plc-insecure-protocol-port", // PORT := 502
"plc-hardcoded-credential", // HmiPassword := 'admin123'
"plc-safety-bypass", // Safety_Enable := FALSE
] {
assert!(
rules.contains(r),
"expected rule {r} from FBD; got {rules:?}"
);
}
}
}
-766
View File
@@ -1,766 +0,0 @@
//! Recursive-descent parser for the security-relevant subset of Structured Text.
//!
//! Tolerant by design: it parses the POUs, variable sections, and statement
//! bodies it understands, and skips (with statement/POU-level recovery) anything
//! it does not, so a single odd construct never sinks the whole file.
use super::ast::*;
use super::lexer::{Keyword as K, Tok, Token};
pub struct Parser {
toks: Vec<Token>,
pos: usize,
}
impl Parser {
pub fn new(toks: Vec<Token>) -> Self {
Self { toks, pos: 0 }
}
// ── token helpers ──────────────────────────────────────────────
fn peek(&self) -> &Tok {
&self.toks[self.pos.min(self.toks.len() - 1)].kind
}
fn line(&self) -> u32 {
self.toks[self.pos.min(self.toks.len() - 1)].line
}
fn at_end(&self) -> bool {
matches!(self.peek(), Tok::Eof)
}
fn advance(&mut self) -> Tok {
let t = self.toks[self.pos.min(self.toks.len() - 1)].kind.clone();
if self.pos < self.toks.len() - 1 {
self.pos += 1;
}
t
}
fn eat(&mut self, t: &Tok) -> bool {
if self.peek() == t {
self.advance();
true
} else {
false
}
}
fn eat_kw(&mut self, k: K) -> bool {
if matches!(self.peek(), Tok::Kw(x) if *x == k) {
self.advance();
true
} else {
false
}
}
fn at_kw(&self, k: K) -> bool {
matches!(self.peek(), Tok::Kw(x) if *x == k)
}
fn ident(&mut self) -> Option<String> {
if let Tok::Ident(s) = self.peek() {
let s = s.clone();
self.advance();
Some(s)
} else {
None
}
}
// ── top level ──────────────────────────────────────────────────
/// Parse every POU in the token stream.
pub fn parse_units(&mut self) -> Vec<Pou> {
let mut pous = Vec::new();
while !self.at_end() {
match self.peek() {
Tok::Kw(K::Program) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Program, K::EndProgram) {
pous.push(p);
}
}
Tok::Kw(K::Function) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::Function, K::EndFunction) {
pous.push(p);
}
}
Tok::Kw(K::FunctionBlock) => {
self.advance();
if let Some(p) = self.parse_pou(PouKind::FunctionBlock, K::EndFunctionBlock) {
pous.push(p);
}
}
// Skip TYPE...END_TYPE and anything else at top level.
_ => {
self.advance();
}
}
}
pous
}
fn parse_pou(&mut self, kind: PouKind, end: K) -> Option<Pou> {
let line = self.line();
let name = self.ident().unwrap_or_else(|| "<anonymous>".to_string());
// Optional `: return_type` for functions.
if self.eat(&Tok::Colon) {
let _ = self.advance(); // return type token
}
let mut vars = Vec::new();
// Variable sections precede the body.
while let Some(section) = self.var_section_kw() {
self.advance();
let _ = self.eat_kw(K::Constant); // CONSTANT is informational for our rules
self.parse_var_decls(section, &mut vars);
}
// Body statements until END_<kind>.
let mut body = Vec::new();
while !self.at_end() && !self.at_kw(end) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
self.eat_kw(end);
Some(Pou {
name,
kind,
vars,
body,
line,
})
}
fn var_section_kw(&self) -> Option<VarSection> {
match self.peek() {
Tok::Kw(K::Var) => Some(VarSection::Var),
Tok::Kw(K::VarInput) => Some(VarSection::Input),
Tok::Kw(K::VarOutput) => Some(VarSection::Output),
Tok::Kw(K::VarInOut) => Some(VarSection::InOut),
Tok::Kw(K::VarGlobal) => Some(VarSection::Global),
Tok::Kw(K::VarTemp) => Some(VarSection::Temp),
Tok::Kw(K::VarExternal) => Some(VarSection::External),
_ => None,
}
}
fn parse_var_decls(&mut self, section: VarSection, out: &mut Vec<VarDecl>) {
while !self.at_end() && !self.at_kw(K::EndVar) {
let line = self.line();
// names: a, b, c
let mut names = Vec::new();
match self.ident() {
Some(n) => names.push(n),
None => {
// Not a declaration we understand — skip to next ; or END_VAR.
self.sync_decl();
continue;
}
}
while self.eat(&Tok::Comma) {
if let Some(n) = self.ident() {
names.push(n);
}
}
if !self.eat(&Tok::Colon) {
self.sync_decl();
continue;
}
let (type_name, array_bounds) = self.parse_type();
let init = if self.eat(&Tok::Assign) {
Some(self.parse_expr())
} else {
None
};
self.eat(&Tok::Semi);
for n in names {
out.push(VarDecl {
name: n,
section,
type_name: type_name.clone(),
array_bounds,
init: init.clone(),
line,
});
}
}
self.eat_kw(K::EndVar);
}
/// Parse a (possibly ARRAY) type, returning its rendered name and literal
/// bounds when present.
fn parse_type(&mut self) -> (String, Option<(i64, i64)>) {
if self.eat_kw(K::Array) {
let mut bounds = None;
if self.eat(&Tok::LBrack) {
let lo = self.int_lit();
self.eat(&Tok::DotDot);
let hi = self.int_lit();
if let (Some(lo), Some(hi)) = (lo, hi) {
bounds = Some((lo, hi));
}
// Skip any further dimensions / tokens to the closing bracket.
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
self.eat_kw(K::Of);
let elem = self.type_ident();
(format!("ARRAY OF {elem}"), bounds)
} else {
(self.type_ident(), None)
}
}
fn type_ident(&mut self) -> String {
// Types can be qualified idents; keep it simple: one token, plus any
// string-length suffix like STRING[80].
let base = match self.advance() {
Tok::Ident(s) => s,
Tok::Kw(_) => "TYPE".to_string(),
other => format!("{other:?}"),
};
if self.eat(&Tok::LBrack) {
while !self.at_end() && !self.eat(&Tok::RBrack) {
self.advance();
}
}
base
}
fn int_lit(&mut self) -> Option<i64> {
match self.peek() {
Tok::Int(n) => {
let n = *n;
self.advance();
Some(n)
}
Tok::Minus => {
self.advance();
if let Tok::Int(n) = self.peek() {
let n = -*n;
self.advance();
Some(n)
} else {
None
}
}
_ => None,
}
}
fn sync_decl(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) && !self.at_kw(K::EndVar) {
self.advance();
}
}
fn sync_stmt(&mut self) {
while !self.at_end() && !self.eat(&Tok::Semi) {
// Stop at block terminators so recovery doesn't swallow structure.
if matches!(
self.peek(),
Tok::Kw(
K::EndIf
| K::EndFor
| K::EndWhile
| K::EndCase
| K::EndRepeat
| K::EndProgram
| K::EndFunction
| K::EndFunctionBlock
| K::Else
| K::Elsif
)
) {
return;
}
self.advance();
}
}
// ── statements ─────────────────────────────────────────────────
fn parse_stmt(&mut self) -> Option<Stmt> {
let line = self.line();
match self.peek().clone() {
Tok::Semi => {
self.advance();
None
}
Tok::Kw(K::If) => self.parse_if(),
Tok::Kw(K::Case) => self.parse_case(),
Tok::Kw(K::For) => self.parse_for(),
Tok::Kw(K::While) => self.parse_while(),
Tok::Kw(K::Repeat) => self.parse_repeat(),
Tok::Kw(K::Return) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Return { line })
}
Tok::Kw(K::Exit) => {
self.advance();
self.eat(&Tok::Semi);
Some(Stmt::Exit { line })
}
Tok::Kw(K::Jmp) => {
self.advance();
let label = self.ident().unwrap_or_default();
self.eat(&Tok::Semi);
Some(Stmt::Jump { label, line })
}
Tok::Ident(name) => {
// Could be `label:`, `call(...)`, or an assignment.
// Lookahead: ident ':' (not ':=') → label.
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Colon)
) && !matches!(self.toks.get(self.pos + 2).map(|t| &t.kind), Some(Tok::Eq))
{
self.advance(); // ident
self.advance(); // ':'
return Some(Stmt::Label { name, line });
}
let lhs = self.parse_expr();
if self.eat(&Tok::Assign) {
let value = self.parse_expr();
self.eat(&Tok::Semi);
Some(Stmt::Assign {
target: lhs,
value,
line,
})
} else if let Expr::Call { callee, args, .. } = lhs {
self.eat(&Tok::Semi);
Some(Stmt::Call { callee, args, line })
} else {
// Bare expression / FB invocation without args recognized —
// skip to the terminator.
self.sync_stmt();
None
}
}
_ => {
self.sync_stmt();
None
}
}
}
fn parse_block_until(&mut self, terms: &[K]) -> Vec<Stmt> {
let mut body = Vec::new();
while !self.at_end() && !terms.iter().any(|k| self.at_kw(*k)) {
if let Some(s) = self.parse_stmt() {
body.push(s);
}
}
body
}
fn parse_if(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::If);
let mut branches = Vec::new();
let cond = self.parse_expr();
self.eat_kw(K::Then);
let body = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((cond, body));
while self.eat_kw(K::Elsif) {
let c = self.parse_expr();
self.eat_kw(K::Then);
let b = self.parse_block_until(&[K::Elsif, K::Else, K::EndIf]);
branches.push((c, b));
}
let else_body = if self.eat_kw(K::Else) {
Some(self.parse_block_until(&[K::EndIf]))
} else {
None
};
self.eat_kw(K::EndIf);
self.eat(&Tok::Semi);
Some(Stmt::If {
branches,
else_body,
line,
})
}
fn parse_case(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Case);
let selector = self.parse_expr();
self.eat_kw(K::Of);
let mut arms = Vec::new();
let mut else_body = None;
while !self.at_end() && !self.at_kw(K::EndCase) {
if self.eat_kw(K::Else) {
else_body = Some(self.parse_block_until(&[K::EndCase]));
break;
}
// labels: expr {, expr} :
let mut labels = vec![self.parse_expr()];
while self.eat(&Tok::Comma) {
labels.push(self.parse_expr());
}
self.eat(&Tok::Colon);
let body = self.parse_block_until(&[K::EndCase, K::Else]);
arms.push((labels, body));
}
self.eat_kw(K::EndCase);
self.eat(&Tok::Semi);
Some(Stmt::Case {
selector,
arms,
else_body,
line,
})
}
fn parse_for(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::For);
let var = self.ident().unwrap_or_default();
self.eat(&Tok::Assign);
let from = self.parse_expr();
self.eat_kw(K::To);
let to = self.parse_expr();
let by = if self.eat_kw(K::By) {
Some(self.parse_expr())
} else {
None
};
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndFor]);
self.eat_kw(K::EndFor);
self.eat(&Tok::Semi);
Some(Stmt::For {
var,
from,
to,
by,
body,
line,
})
}
fn parse_while(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::While);
let cond = self.parse_expr();
self.eat_kw(K::Do);
let body = self.parse_block_until(&[K::EndWhile]);
self.eat_kw(K::EndWhile);
self.eat(&Tok::Semi);
Some(Stmt::While { cond, body, line })
}
fn parse_repeat(&mut self) -> Option<Stmt> {
let line = self.line();
self.eat_kw(K::Repeat);
let body = self.parse_block_until(&[K::Until, K::EndRepeat]);
self.eat_kw(K::Until);
let until = self.parse_expr();
self.eat_kw(K::EndRepeat);
self.eat(&Tok::Semi);
Some(Stmt::Repeat { body, until, line })
}
// ── expressions (precedence climbing) ──────────────────────────
pub fn parse_expr(&mut self) -> Expr {
self.parse_or()
}
fn parse_or(&mut self) -> Expr {
let mut lhs = self.parse_and();
loop {
let op = match self.peek() {
Tok::Kw(K::Or) => BinOp::Or,
Tok::Kw(K::Xor) => BinOp::Xor,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_and();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_and(&mut self) -> Expr {
let mut lhs = self.parse_cmp();
while matches!(self.peek(), Tok::Kw(K::And) | Tok::Amp) {
let op = BinOp::And;
let line = self.line();
self.advance();
let rhs = self.parse_cmp();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_cmp(&mut self) -> Expr {
let mut lhs = self.parse_add();
loop {
let op = match self.peek() {
Tok::Eq => BinOp::Eq,
Tok::Ne => BinOp::Ne,
Tok::Lt => BinOp::Lt,
Tok::Le => BinOp::Le,
Tok::Gt => BinOp::Gt,
Tok::Ge => BinOp::Ge,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_add();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_add(&mut self) -> Expr {
let mut lhs = self.parse_mul();
loop {
let op = match self.peek() {
Tok::Plus => BinOp::Add,
Tok::Minus => BinOp::Sub,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_mul();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_mul(&mut self) -> Expr {
let mut lhs = self.parse_unary();
loop {
let op = match self.peek() {
Tok::Star => BinOp::Mul,
Tok::Slash => BinOp::Div,
Tok::Kw(K::Mod) => BinOp::Mod,
Tok::Power => BinOp::Pow,
_ => break,
};
let line = self.line();
self.advance();
let rhs = self.parse_unary();
lhs = Expr::Binary {
op,
lhs: Box::new(lhs),
rhs: Box::new(rhs),
line,
};
}
lhs
}
fn parse_unary(&mut self) -> Expr {
let line = self.line();
match self.peek() {
Tok::Kw(K::Not) => {
self.advance();
Expr::Unary {
op: UnOp::Not,
expr: Box::new(self.parse_unary()),
line,
}
}
Tok::Minus => {
self.advance();
Expr::Unary {
op: UnOp::Neg,
expr: Box::new(self.parse_unary()),
line,
}
}
_ => self.parse_postfix(),
}
}
fn parse_postfix(&mut self) -> Expr {
let mut e = self.parse_primary();
loop {
let line = self.line();
match self.peek() {
Tok::LBrack => {
self.advance();
let index = self.parse_expr();
self.eat(&Tok::RBrack);
e = Expr::Index {
base: Box::new(e),
index: Box::new(index),
line,
};
}
Tok::Dot => {
self.advance();
let field = self.ident().unwrap_or_default();
e = Expr::Member {
base: Box::new(e),
field,
line,
};
}
_ => break,
}
}
e
}
fn parse_primary(&mut self) -> Expr {
let line = self.line();
match self.advance() {
Tok::Int(n) => Expr::Int(n, line),
Tok::Real(r) => Expr::Real(r, line),
Tok::Bool(b) => Expr::Bool(b, line),
Tok::Str(s) => Expr::Str(s, line),
Tok::Time(t) => Expr::Time(t, line),
Tok::LParen => {
let e = self.parse_expr();
self.eat(&Tok::RParen);
e
}
Tok::Ident(name) => {
if self.eat(&Tok::LParen) {
let args = self.parse_call_args();
Expr::Call {
callee: name,
args,
line,
}
} else {
Expr::Ident(name, line)
}
}
// Unrecognized start of expression — yield a placeholder identifier.
_ => Expr::Ident(String::new(), line),
}
}
fn parse_call_args(&mut self) -> Vec<CallArg> {
let mut args = Vec::new();
if self.eat(&Tok::RParen) {
return args;
}
loop {
// Named arg: ident := expr (peek two tokens).
if let Tok::Ident(name) = self.peek().clone() {
if matches!(
self.toks.get(self.pos + 1).map(|t| &t.kind),
Some(Tok::Assign)
) {
self.advance(); // ident
self.advance(); // :=
let value = self.parse_expr();
args.push(CallArg {
name: Some(name),
value,
});
if self.eat(&Tok::Comma) {
continue;
}
break;
}
}
let value = self.parse_expr();
args.push(CallArg { name: None, value });
if self.eat(&Tok::Comma) {
continue;
}
break;
}
self.eat(&Tok::RParen);
args
}
}
/// Parse ST source into its POUs.
pub fn parse(src: &str) -> Vec<Pou> {
let toks = super::lexer::lex(src);
Parser::new(toks).parse_units()
}
#[cfg(test)]
mod tests {
use super::*;
const SAMPLE: &str = r#"
PROGRAM Main
VAR
idx : INT;
pw : STRING := 'admin123';
buf : ARRAY[0..9] OF INT;
ok : BOOL := FALSE;
END_VAR
// a comment
IF idx > 0 THEN
buf[idx] := idx * 2;
ELSE
JMP done;
END_IF;
Comm(IP := '10.0.0.1', PORT := 502);
done:
ok := TRUE;
END_PROGRAM
"#;
#[test]
fn parses_program_vars_and_body() {
let pous = parse(SAMPLE);
assert_eq!(pous.len(), 1, "one POU");
let p = &pous[0];
assert_eq!(p.name, "Main");
assert_eq!(p.kind, PouKind::Program);
// vars: idx, pw, buf, ok
assert_eq!(p.vars.len(), 4);
let pw = p.vars.iter().find(|v| v.name == "pw").expect("pw");
assert!(matches!(&pw.init, Some(Expr::Str(s, _)) if s == "admin123"));
let buf = p.vars.iter().find(|v| v.name == "buf").expect("buf");
assert_eq!(buf.array_bounds, Some((0, 9)));
// body has an IF, a Call, a Label, and an Assign
assert!(p.body.iter().any(|s| matches!(s, Stmt::If { .. })));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Call { callee, .. } if callee == "Comm")));
assert!(p
.body
.iter()
.any(|s| matches!(s, Stmt::Label { name, .. } if name == "done")));
}
#[test]
fn jmp_inside_if_is_captured() {
let pous = parse(SAMPLE);
let p = &pous[0];
// find the IF, check its else branch has a JMP
let has_jmp = p.body.iter().any(|s| match s {
Stmt::If { else_body, .. } => else_body
.as_ref()
.map(|b| b.iter().any(|s| matches!(s, Stmt::Jump { .. })))
.unwrap_or(false),
_ => false,
});
assert!(has_jmp, "JMP should be parsed inside the ELSE branch");
}
}
@@ -1,418 +0,0 @@
//! PLCopen XML → Structured Text POUs.
//!
//! A PLCopen project stores each POU as `<pou name=".." pouType="..">` with an
//! `<interface>` (typed variable sections) and a `<body>` in one of the IEC
//! 61131-3 languages. We reconstruct an equivalent Structured-Text source for
//! each POU (a `VAR` block from the interface + statements from the body) and run
//! it through the ST parser, so raw `.st` files and PLCopen projects — textual or
//! graphical — flow through one analysis path.
//!
//! Body languages:
//! - **ST** — taken verbatim.
//! - **FBD / LD** — the graphical network is translated to synthetic ST: blocks
//! become calls (`TypeName(pin := arg, …)`), out-variables / coils become
//! assignments, with input pins resolved by tracing connections. This lets the
//! semantic rules see comm calls, hardcoded arguments and safety writes that
//! live in graphical logic, not just in text.
//! - **SFC** — the step/transition graph itself is skipped; the ST/FBD/LD bodies
//! embedded in its actions and transitions are still translated.
use std::collections::HashMap;
use roxmltree::Node;
use super::ast::Pou;
use super::parser;
/// Parse every POU out of a PLCopen XML document (ST, FBD or LD bodies).
pub fn parse_plcopen(xml: &str) -> Vec<Pou> {
let doc = match roxmltree::Document::parse(xml) {
Ok(d) => d,
Err(_) => return Vec::new(),
};
let mut pous = Vec::new();
for pou in doc.descendants().filter(|n| n.has_tag_name("pou")) {
let name = pou.attribute("name").unwrap_or("pou").to_string();
let pou_type = pou.attribute("pouType").unwrap_or("program");
let Some(body) = reconstruct_body(pou) else {
continue;
};
if body.trim().is_empty() {
continue;
}
let var_block = build_var_block(pou);
let kw = match pou_type.to_ascii_lowercase().as_str() {
"function" => "FUNCTION",
"functionblock" | "functionblocktype" => "FUNCTION_BLOCK",
_ => "PROGRAM",
};
let synthetic = format!("{kw} {name}\n{var_block}{body}\nEND_{kw}\n");
pous.extend(parser::parse(&synthetic));
}
pous
}
/// Case-insensitive tag match (PLCopen uses `FBD`/`LD`/`ST`, CODESYS may vary).
fn tag_is(n: &Node, name: &str) -> bool {
n.tag_name().name().eq_ignore_ascii_case(name)
}
/// Reconstruct a POU's body as Structured Text, whatever language it is written
/// in. Concatenates every language body found under `<body>` (SFC actions and
/// transitions carry their own ST/FBD/LD sub-bodies).
fn reconstruct_body(pou: Node) -> Option<String> {
let mut out = String::new();
for body in pou.descendants().filter(|n| tag_is(n, "body")) {
for lang in body.children().filter(|n| n.is_element()) {
let piece = match lang.tag_name().name().to_ascii_uppercase().as_str() {
"ST" | "IL" => collect_text(lang),
"FBD" | "LD" => translate_network(lang),
_ => continue,
};
if !piece.trim().is_empty() {
out.push_str(&piece);
if !piece.ends_with('\n') {
out.push('\n');
}
}
}
}
if out.trim().is_empty() {
None
} else {
Some(out)
}
}
// ── graphical (FBD / LD) → synthetic ST ────────────────────────────────
/// Translate one FBD/LD network into ST statements: blocks → calls,
/// out-variables and coils → assignments.
fn translate_network(net: Node) -> String {
let by_id = index_local_ids(net);
let mut out = String::new();
for el in net.children().filter(|n| n.is_element()) {
let stmt = match el.tag_name().name().to_ascii_lowercase().as_str() {
"block" => block_call(el, &by_id).map(|c| format!("{c};")),
"outvariable" => out_assignment(el, &by_id),
"coil" => coil_assignment(el, &by_id),
_ => None,
};
if let Some(s) = stmt {
out.push_str(&s);
out.push('\n');
}
}
out
}
/// Index every element in a network by its `localId` so connections resolve.
fn index_local_ids<'a, 'input>(net: Node<'a, 'input>) -> HashMap<String, Node<'a, 'input>> {
net.descendants()
.filter(|n| n.is_element())
.filter_map(|n| n.attribute("localId").map(|id| (id.to_string(), n)))
.collect()
}
/// Build a call expression for a block: `TypeName(pin := arg, …)`.
fn block_call(block: Node, by_id: &HashMap<String, Node>) -> Option<String> {
let ty = block.attribute("typeName")?;
let mut args = Vec::new();
if let Some(inputs) = block.children().find(|n| tag_is(n, "inputVariables")) {
for v in inputs.children().filter(|n| tag_is(n, "variable")) {
let Some(expr) = input_expr(v, by_id, 0) else {
continue;
};
match v.attribute("formalParameter") {
Some(pin) if !pin.is_empty() => args.push(format!("{pin} := {expr}")),
_ => args.push(expr),
}
}
}
Some(format!("{ty}({})", args.join(", ")))
}
/// `target := <traced expression>;` for an FBD out-variable.
fn out_assignment(outvar: Node, by_id: &HashMap<String, Node>) -> Option<String> {
let target = expression_text(outvar)?;
let value = input_expr(outvar, by_id, 0).unwrap_or_else(|| "0".to_string());
Some(format!("{target} := {value};"))
}
/// `coil := <traced rung expression>;` for an LD coil (negated → `NOT (…)`).
fn coil_assignment(coil: Node, by_id: &HashMap<String, Node>) -> Option<String> {
let target = child_text(coil, "variable")?;
let rung = input_expr(coil, by_id, 0).unwrap_or_else(|| "TRUE".to_string());
let negated = matches!(coil.attribute("negated"), Some(v) if v.eq_ignore_ascii_case("true"));
let rhs = if negated {
format!("NOT ({rung})")
} else {
rung
};
Some(format!("{target} := {rhs};"))
}
/// Resolve the expression feeding `node`'s single input connection.
fn input_expr(node: Node, by_id: &HashMap<String, Node>, depth: u8) -> Option<String> {
let refid = ref_local_id(node)?;
Some(expr_for(&refid, by_id, depth))
}
/// Build the ST expression produced by the element with this `localId`.
fn expr_for(local_id: &str, by_id: &HashMap<String, Node>, depth: u8) -> String {
if depth > 24 {
return "0".to_string();
}
let Some(node) = by_id.get(local_id) else {
return format!("__net{local_id}");
};
match node.tag_name().name().to_ascii_lowercase().as_str() {
"invariable" | "inoutvariable" => {
expression_text(*node).unwrap_or_else(|| format!("__net{local_id}"))
}
// A block feeding another element: reference it by a synthetic result
// name; the block is emitted as its own call statement, so we neither
// duplicate the call nor lose it.
"block" => format!("__blk{local_id}"),
"contact" => {
let var = child_text(*node, "variable").unwrap_or_else(|| "TRUE".to_string());
let negated =
matches!(node.attribute("negated"), Some(v) if v.eq_ignore_ascii_case("true"));
let term = if negated { format!("NOT {var}") } else { var };
match ref_local_id(*node) {
Some(up) => {
let upstream = expr_for(&up, by_id, depth + 1);
if upstream == "TRUE" {
term
} else {
format!("({upstream} AND {term})")
}
}
None => term,
}
}
"leftpowerrail" => "TRUE".to_string(),
_ => format!("__net{local_id}"),
}
}
/// The `refLocalId` of `node`'s first input connection, if any.
fn ref_local_id(node: Node) -> Option<String> {
node.descendants()
.find(|n| tag_is(n, "connectionPointIn"))
.and_then(|cpi| cpi.descendants().find(|n| tag_is(n, "connection")))
.and_then(|c| c.attribute("refLocalId"))
.map(|s| s.to_string())
}
/// Text of a node's `<expression>` child (variable name or literal).
fn expression_text(node: Node) -> Option<String> {
let e = node.children().find(|n| tag_is(n, "expression"))?;
let t = collect_text(e).trim().to_string();
if t.is_empty() {
None
} else {
Some(t)
}
}
/// Text of a named child element (e.g. `<variable>` of a contact/coil).
fn child_text(node: Node, name: &str) -> Option<String> {
let c = node.children().find(|n| tag_is(n, name))?;
let t = collect_text(c).trim().to_string();
if t.is_empty() {
None
} else {
Some(t)
}
}
/// Concatenate the text of a node's descendant text nodes (bodies are often
/// wrapped in `<xhtml>` and may contain multiple text runs). Only text nodes are
/// gathered: an element's `.text()` would re-yield its first child's text, which
/// (with the text node itself) would duplicate every value.
fn collect_text(node: Node) -> String {
node.descendants()
.filter(|n| n.is_text())
.filter_map(|n| n.text())
.collect::<String>()
}
/// Build an ST `VAR … END_VAR` block from a POU's `<interface>` variable
/// sections, so declarations (types, initial values) reach the rules.
fn build_var_block(pou: Node) -> String {
let Some(interface) = pou.children().find(|n| n.has_tag_name("interface")) else {
return String::new();
};
let mut out = String::from("VAR\n");
let mut any = false;
for container in interface.children().filter(|n| n.is_element()) {
// localVars / inputVars / outputVars / inOutVars / tempVars / globalVars / externalVars
if !container.tag_name().name().ends_with("Vars") {
continue;
}
for var in container.children().filter(|n| n.has_tag_name("variable")) {
let Some(vname) = var.attribute("name") else {
continue;
};
let ty = var
.children()
.find(|n| n.has_tag_name("type"))
.map(type_name)
.unwrap_or_else(|| "BOOL".to_string());
let init = var
.children()
.find(|n| n.has_tag_name("initialValue"))
.and_then(initial_value);
match init {
Some(v) => out.push_str(&format!(" {vname} : {ty} := {v};\n")),
None => out.push_str(&format!(" {vname} : {ty};\n")),
}
any = true;
}
}
out.push_str("END_VAR\n");
if any {
out
} else {
String::new()
}
}
/// Render a PLCopen `<type>` element as an ST type string.
fn type_name(type_node: Node) -> String {
let Some(inner) = type_node.children().find(|n| n.is_element()) else {
return "BOOL".to_string();
};
let tag = inner.tag_name().name();
match tag {
"derived" => inner.attribute("name").unwrap_or("DERIVED").to_string(),
"array" => {
let dim = inner.children().find(|n| n.has_tag_name("dimension"));
let (lo, hi) = dim
.map(|d| {
(
d.attribute("lower").unwrap_or("0").to_string(),
d.attribute("upper").unwrap_or("0").to_string(),
)
})
.unwrap_or_else(|| ("0".to_string(), "0".to_string()));
let base = inner
.children()
.find(|n| n.has_tag_name("baseType"))
.map(type_name)
.unwrap_or_else(|| "INT".to_string());
format!("ARRAY[{lo}..{hi}] OF {base}")
}
"string" | "wstring" => "STRING".to_string(),
// BOOL, INT, DINT, REAL, TIME, ... — the tag name is the ST type.
other => other.to_ascii_uppercase(),
}
}
/// Extract an initial value as an ST literal (quoting strings).
fn initial_value(iv: Node) -> Option<String> {
let simple = iv.descendants().find(|n| n.has_tag_name("simpleValue"))?;
let raw = simple.attribute("value")?.trim().to_string();
if raw.is_empty() {
return None;
}
// Numbers / booleans / time literals pass through; everything else is a
// string literal.
let is_scalar = raw.eq_ignore_ascii_case("true")
|| raw.eq_ignore_ascii_case("false")
|| raw.starts_with(['T', 't', 'D', 'd']) && raw.contains('#')
|| raw
.chars()
.all(|c| c.is_ascii_digit() || c == '.' || c == '-' || c == '+');
if is_scalar || raw.starts_with('\'') || raw.starts_with('"') {
Some(raw)
} else {
Some(format!("'{}'", raw.replace('\'', "''")))
}
}
#[cfg(test)]
mod tests {
use super::parse_plcopen;
use crate::pipeline::plc::rules;
use std::collections::HashSet;
fn rule_ids(xml: &str) -> HashSet<&'static str> {
parse_plcopen(xml)
.iter()
.flat_map(rules::analyze)
.map(|h| h.rule_id)
.collect()
}
/// A Ladder Diagram network: a rung (power rail → contact → coil) plus an
/// insecure comm block. Coils/contacts translate to assignments; the block
/// translates to a call so the port rule fires.
#[test]
fn ld_coil_and_block_translate_and_are_analysed() {
let xml = r#"<?xml version="1.0"?>
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types><pous>
<pou name="Rung" pouType="program">
<interface><localVars>
<variable name="Motor"><type><BOOL/></type></variable>
</localVars></interface>
<body><LD>
<leftPowerRail localId="0"/>
<contact localId="1"><variable>Start</variable>
<connectionPointIn><connection refLocalId="0"/></connectionPointIn></contact>
<coil localId="2"><variable>Motor</variable>
<connectionPointIn><connection refLocalId="1"/></connectionPointIn></coil>
<inVariable localId="3"><expression>21</expression></inVariable>
<inVariable localId="4"><expression>FALSE</expression></inVariable>
<block localId="10" typeName="Ftp_Send">
<inputVariables>
<variable formalParameter="PORT">
<connectionPointIn><connection refLocalId="3"/></connectionPointIn></variable>
<variable formalParameter="ENCRYPT">
<connectionPointIn><connection refLocalId="4"/></connectionPointIn></variable>
</inputVariables>
</block>
</LD></body>
</pou>
</pous></types>
</project>"#;
let ids = rule_ids(xml);
// Ftp_Send(PORT := 21, ENCRYPT := FALSE) — port 21 is an insecure protocol.
assert!(
ids.contains("plc-insecure-protocol-port"),
"LD block should flag port 21; got {ids:?}"
);
}
/// Doubled-text regression: a graphical expression must be extracted once,
/// so literals like `502` and `FALSE` stay intact (not `502502`/`FALSEFALSE`).
#[test]
fn graphical_expression_text_is_not_duplicated() {
let xml = r#"<?xml version="1.0"?>
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types><pous>
<pou name="Comm" pouType="program">
<body><FBD>
<inVariable localId="1"><expression>502</expression></inVariable>
<inVariable localId="2"><expression>FALSE</expression></inVariable>
<block localId="10" typeName="Modbus_TCP_Master">
<inputVariables>
<variable formalParameter="PORT">
<connectionPointIn><connection refLocalId="1"/></connectionPointIn></variable>
<variable formalParameter="AUTH">
<connectionPointIn><connection refLocalId="2"/></connectionPointIn></variable>
</inputVariables>
</block>
</FBD></body>
</pou>
</pous></types>
</project>"#;
let ids = rule_ids(xml);
assert!(ids.contains("plc-insecure-protocol-port")); // PORT := 502 (not 502502)
assert!(ids.contains("plc-insecure-comm")); // AUTH := FALSE (not FALSEFALSE)
}
}
-632
View File
@@ -1,632 +0,0 @@
//! Semantic control-logic security rules over the Structured Text AST.
//!
//! Each rule walks the parsed [`Pou`] and yields [`RuleHit`]s the scanner turns
//! into findings. Rules reason over structure (declarations, assignments, calls,
//! array accesses, division, jumps) rather than raw text, so they see through
//! formatting and comments.
use std::collections::{HashMap, HashSet};
use compliance_core::models::Severity;
use super::ast::*;
/// One rule match within a POU.
pub struct RuleHit {
pub line: u32,
pub severity: Severity,
pub rule_id: &'static str,
pub title: String,
pub description: String,
pub cwe: Option<&'static str>,
pub remediation: &'static str,
}
/// Run every rule over a POU.
pub fn analyze(pou: &Pou) -> Vec<RuleHit> {
let mut hits = Vec::new();
let ctx = Ctx::build(pou);
// Declaration-level rules.
for v in &pou.vars {
if let Some(init) = &v.init {
check_credential_binding(&v.name, init, &pou.name, &mut hits);
check_default_password(init, &v.name, &pou.name, &mut hits);
}
}
// Body walk.
walk(&pou.body, pou, &ctx, &GuardSet::default(), &mut hits);
hits
}
/// Per-POU context precomputed once.
struct Ctx {
/// Names declared in VAR_INPUT (untrusted / externally driven).
input_vars: HashSet<String>,
/// Array variable name → declared (lo, hi) bounds.
arrays: HashMap<String, (i64, i64)>,
}
impl Ctx {
fn build(pou: &Pou) -> Self {
let mut input_vars = HashSet::new();
let mut arrays = HashMap::new();
for v in &pou.vars {
if v.section == VarSection::Input {
input_vars.insert(v.name.to_ascii_lowercase());
}
if let Some(b) = v.array_bounds {
arrays.insert(v.name.to_ascii_lowercase(), b);
}
}
Self { input_vars, arrays }
}
}
/// Variables proven non-zero on the current control-flow path (from enclosing
/// `IF`/`WHILE` conditions), so guarded divisions aren't false-flagged.
#[derive(Default, Clone)]
struct GuardSet {
nonzero: HashSet<String>,
}
impl GuardSet {
fn with(&self, names: Vec<String>) -> Self {
let mut g = self.clone();
g.nonzero.extend(names);
g
}
fn is_nonzero(&self, name: &str) -> bool {
self.nonzero.contains(name)
}
}
/// Variable names a condition proves non-zero (`v <> 0`, `v > 0`, `v >= 1`,
/// `v < 0`, and conjunctions thereof).
fn guards_from_cond(cond: &Expr) -> Vec<String> {
let mut out = Vec::new();
collect_nonzero(cond, &mut out);
out
}
fn collect_nonzero(e: &Expr, out: &mut Vec<String>) {
let Expr::Binary { op, lhs, rhs, .. } = e else {
return;
};
let is_zero = |x: &Expr| {
matches!(x, Expr::Int(0, _)) || matches!(x, Expr::Real(r, _) if r.abs() < f64::EPSILON)
};
let int_of = |x: &Expr| match x {
Expr::Int(n, _) => Some(*n),
_ => None,
};
match op {
BinOp::And => {
collect_nonzero(lhs, out);
collect_nonzero(rhs, out);
}
BinOp::Ne => {
if let (Some(v), true) = (lhs.as_ident(), is_zero(rhs)) {
out.push(v.to_ascii_lowercase());
}
if let (true, Some(v)) = (is_zero(lhs), rhs.as_ident()) {
out.push(v.to_ascii_lowercase());
}
}
BinOp::Gt | BinOp::Lt => {
// v > 0 or v < 0
if let (Some(v), true) = (lhs.as_ident(), is_zero(rhs)) {
out.push(v.to_ascii_lowercase());
}
}
BinOp::Ge => {
// v >= n, n >= 1
if let (Some(v), Some(n)) = (lhs.as_ident(), int_of(rhs)) {
if n >= 1 {
out.push(v.to_ascii_lowercase());
}
}
}
_ => {}
}
}
// ── the walker ─────────────────────────────────────────────────────
fn walk(stmts: &[Stmt], pou: &Pou, ctx: &Ctx, guards: &GuardSet, hits: &mut Vec<RuleHit>) {
for s in stmts {
match s {
Stmt::Assign {
target,
value,
line,
} => {
check_safety_bypass(target, value, *line, &pou.name, hits);
// A string bound to a secret-looking target is a credential.
if let Some(name) = flatten_ident(target) {
check_credential_binding(&name, value, &pou.name, hits);
check_default_password(value, &name, &pou.name, hits);
}
walk_expr(target, pou, ctx, guards, hits);
walk_expr(value, pou, ctx, guards, hits);
}
Stmt::Call { callee, args, line } => {
check_insecure_comm(callee, args, *line, &pou.name, hits);
check_credentials_in_call(callee, args, *line, &pou.name, hits);
for a in args {
walk_expr(&a.value, pou, ctx, guards, hits);
}
}
Stmt::Jump { label, line } => hits.push(RuleHit {
line: *line,
severity: Severity::Medium,
rule_id: "plc-unstructured-jump",
title: "Unstructured jump (JMP) in control logic".to_string(),
description: format!(
"POU `{}` uses `JMP {label}`. Unstructured jumps make control flow hard to \
verify and can bypass safety interlocks or leave outputs in an undefined \
state on unexpected paths.",
pou.name
),
cwe: Some("CWE-691"),
remediation: "Replace JMP with structured constructs (IF/CASE/loops); reserve \
jumps for well-reviewed state machines only.",
}),
Stmt::If {
branches,
else_body,
..
} => {
for (cond, body) in branches {
walk_expr(cond, pou, ctx, guards, hits);
let child = guards.with(guards_from_cond(cond));
walk(body, pou, ctx, &child, hits);
}
if let Some(b) = else_body {
walk(b, pou, ctx, guards, hits);
}
}
Stmt::Case {
selector,
arms,
else_body,
..
} => {
walk_expr(selector, pou, ctx, guards, hits);
for (labels, body) in arms {
for l in labels {
walk_expr(l, pou, ctx, guards, hits);
}
walk(body, pou, ctx, guards, hits);
}
if let Some(b) = else_body {
walk(b, pou, ctx, guards, hits);
}
}
Stmt::For {
from, to, by, body, ..
} => {
walk_expr(from, pou, ctx, guards, hits);
walk_expr(to, pou, ctx, guards, hits);
if let Some(b) = by {
walk_expr(b, pou, ctx, guards, hits);
}
walk(body, pou, ctx, guards, hits);
}
Stmt::While { cond, body, .. } => {
walk_expr(cond, pou, ctx, guards, hits);
let child = guards.with(guards_from_cond(cond));
walk(body, pou, ctx, &child, hits);
}
Stmt::Repeat { body, until, .. } => {
walk(body, pou, ctx, guards, hits);
walk_expr(until, pou, ctx, guards, hits);
}
Stmt::Return { .. } | Stmt::Exit { .. } | Stmt::Label { .. } => {}
}
}
}
fn walk_expr(e: &Expr, pou: &Pou, ctx: &Ctx, guards: &GuardSet, hits: &mut Vec<RuleHit>) {
match e {
Expr::Index { base, index, line } => {
check_array_bounds(base, index, *line, ctx, &pou.name, hits);
walk_expr(base, pou, ctx, guards, hits);
walk_expr(index, pou, ctx, guards, hits);
}
Expr::Binary { op, lhs, rhs, line } => {
if matches!(op, BinOp::Div | BinOp::Mod) {
check_division(rhs, *line, &pou.name, guards, hits);
}
walk_expr(lhs, pou, ctx, guards, hits);
walk_expr(rhs, pou, ctx, guards, hits);
}
Expr::Unary { expr, .. } => walk_expr(expr, pou, ctx, guards, hits),
Expr::Member { base, .. } => walk_expr(base, pou, ctx, guards, hits),
Expr::Call { args, .. } => {
for a in args {
walk_expr(&a.value, pou, ctx, guards, hits);
}
}
_ => {}
}
}
// ── individual rules ───────────────────────────────────────────────
const SECRET_HINTS: &[&str] = &[
"password",
"passwd",
"pwd",
"secret",
"apikey",
"api_key",
"token",
"credential",
"privkey",
"private_key",
"passphrase",
];
const DEFAULT_PASSWORDS: &[&str] = &[
"admin",
"administrator",
"password",
"passwd",
"1234",
"12345",
"123456",
"0000",
"1111",
"root",
"default",
"admin123",
"changeme",
"letmein",
"guest",
"user",
"system",
"plc",
"codesys",
];
const COMM_FB_HINTS: &[&str] = &[
"modbus", "tcp", "udp", "socket", "mqtt", "opcua", "opc_ua", "ethernet", "ethip", "enip",
"dnp3", "ftp", "telnet", "http", "send", "connect", "sock", "comm", "profinet", "s7",
];
/// Insecure cleartext service ports.
const INSECURE_PORTS: &[i64] = &[21, 23, 80, 502, 20000, 44818, 102];
fn check_credential_binding(var_name: &str, value: &Expr, pou: &str, hits: &mut Vec<RuleHit>) {
let name = var_name.to_ascii_lowercase();
let looks_secret = SECRET_HINTS.iter().any(|h| name.contains(h));
if looks_secret {
if let Expr::Str(s, line) = value {
if !s.is_empty() {
hits.push(RuleHit {
line: *line,
severity: Severity::High,
rule_id: "plc-hardcoded-credential",
title: "Hardcoded credential in PLC program".to_string(),
description: format!(
"POU `{pou}` binds a hardcoded secret to `{var_name}`. Credentials \
embedded in control logic are extracted trivially from a project export \
or a firmware dump and cannot be rotated without a redeploy."
),
cwe: Some("CWE-798"),
remediation: "Store secrets outside the program (secure parameter store / \
operator-entered, retained-but-protected memory); never commit \
them to the POU.",
});
}
}
}
}
fn check_default_password(value: &Expr, var_name: &str, pou: &str, hits: &mut Vec<RuleHit>) {
if let Expr::Str(s, line) = value {
let lower = s.to_ascii_lowercase();
if DEFAULT_PASSWORDS.contains(&lower.as_str()) {
hits.push(RuleHit {
line: *line,
severity: Severity::Critical,
rule_id: "plc-default-password",
title: "Default/weak password in PLC program".to_string(),
description: format!(
"POU `{pou}` uses the well-known default/weak password `{s}` (bound to \
`{var_name}`). Default PLC credentials are the first thing an attacker tries."
),
cwe: Some("CWE-1393"),
remediation:
"Require a strong, unique, operator-set password; block commissioning \
until the default is changed.",
});
}
}
}
fn check_credentials_in_call(
callee: &str,
args: &[CallArg],
line: u32,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
for a in args {
if let Some(name) = &a.name {
let n = name.to_ascii_lowercase();
if SECRET_HINTS.iter().any(|h| n.contains(h)) {
if let Expr::Str(s, l) = &a.value {
if !s.is_empty() {
hits.push(RuleHit {
line: *l,
severity: Severity::High,
rule_id: "plc-hardcoded-credential",
title: "Hardcoded credential passed to a function block".to_string(),
description: format!(
"POU `{pou}` passes a hardcoded secret as `{name}` to `{callee}`."
),
cwe: Some("CWE-798"),
remediation: "Supply credentials from protected configuration at \
runtime, not as a literal argument.",
});
}
}
}
}
}
let _ = line;
}
fn check_safety_bypass(target: &Expr, value: &Expr, line: u32, pou: &str, hits: &mut Vec<RuleHit>) {
let Some(name) = flatten_ident(target) else {
return;
};
let n = name.to_ascii_lowercase();
let safety = [
"safety",
"estop",
"e_stop",
"emergency",
"interlock",
"guard",
"permit",
]
.iter()
.any(|h| n.contains(h));
let watchdog = n.contains("watchdog") || n.contains("wdt");
// A safety enable / interlock / watchdog signal driven to FALSE or 0 in
// application logic is a bypass (e.g. `Safety_Enable := FALSE`, `Watchdog_Kick := 0`).
let disabling = matches!(value, Expr::Bool(false, _)) || matches!(value, Expr::Int(0, _));
if (safety || watchdog) && disabling {
hits.push(RuleHit {
line,
severity: Severity::Critical,
rule_id: "plc-safety-bypass",
title: "Safety interlock / watchdog disabled in logic".to_string(),
description: format!(
"POU `{pou}` disables a safety-related signal (`{name}`) in program logic. \
Bypassing interlocks or watchdogs in code defeats the plant's protective \
functions and is a direct hazard."
),
cwe: Some("CWE-1384"),
remediation: "Never disable safety functions from application logic; safety must be \
handled by a certified safety controller / hard-wired circuit.",
});
}
}
fn check_array_bounds(
base: &Expr,
index: &Expr,
line: u32,
ctx: &Ctx,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
// Only reason about arrays we know the bounds of.
let Some(arr_name) = base.as_ident() else {
return;
};
if !ctx.arrays.contains_key(&arr_name.to_ascii_lowercase()) {
return;
}
// Index by an untrusted input variable → potential out-of-bounds access.
if let Some(idx_name) = index.as_ident() {
if ctx.input_vars.contains(&idx_name.to_ascii_lowercase()) {
hits.push(RuleHit {
line,
severity: Severity::High,
rule_id: "plc-array-unchecked-index",
title: "Array indexed by unvalidated input".to_string(),
description: format!(
"POU `{pou}` indexes array `{arr_name}` with the input variable `{idx_name}` \
without a validated bounds check. An out-of-range index corrupts adjacent \
memory or faults the PLC (loss of control)."
),
cwe: Some("CWE-129"),
remediation: "Clamp or validate the index against the array bounds (e.g. \
`LIMIT`/explicit `IF idx >= lo AND idx <= hi`) before the access.",
});
}
}
}
fn check_division(
divisor: &Expr,
line: u32,
pou: &str,
guards: &GuardSet,
hits: &mut Vec<RuleHit>,
) {
// A divisor proven non-zero by an enclosing guard is safe.
if let Expr::Ident(name, _) = divisor {
if guards.is_nonzero(&name.to_ascii_lowercase()) {
return;
}
}
// Flag division by a variable (could be zero); nonzero literals are fine.
let risky = matches!(
divisor,
Expr::Ident(_, _) | Expr::Member { .. } | Expr::Index { .. } | Expr::Int(0, _)
);
if risky {
hits.push(RuleHit {
line,
severity: Severity::Medium,
rule_id: "plc-division-by-zero",
title: "Division by a variable without a zero-guard".to_string(),
description: format!(
"POU `{pou}` divides by a variable that is not proven non-zero. A zero divisor \
raises a PLC exception and can halt the scan cycle (denial of control)."
),
cwe: Some("CWE-369"),
remediation: "Guard the divisor (`IF d <> 0 THEN …`) or use a safe-divide helper that \
returns a defined value for a zero denominator.",
});
}
}
fn check_insecure_comm(
callee: &str,
args: &[CallArg],
line: u32,
pou: &str,
hits: &mut Vec<RuleHit>,
) {
let c = callee.to_ascii_lowercase();
let is_comm = COMM_FB_HINTS.iter().any(|h| c.contains(h));
if !is_comm {
return;
}
// Auth/encryption explicitly disabled.
for a in args {
if let Some(name) = &a.name {
let n = name.to_ascii_lowercase();
let security_flag = ["auth", "secure", "encrypt", "tls", "ssl", "authentication"]
.iter()
.any(|h| n.contains(h));
if security_flag && matches!(a.value, Expr::Bool(false, _)) {
hits.push(RuleHit {
line,
severity: Severity::High,
rule_id: "plc-insecure-comm",
title: "Network communication with security disabled".to_string(),
description: format!(
"POU `{pou}` calls `{callee}` with `{name} := FALSE`, disabling \
authentication/encryption on an industrial network link."
),
cwe: Some("CWE-319"),
remediation: "Enable authentication + transport encryption; segment OT \
networks and restrict the endpoint to trusted peers.",
});
}
}
// Well-known cleartext port literal.
if let Expr::Int(p, _) = &a.value {
if INSECURE_PORTS.contains(p) {
hits.push(RuleHit {
line,
severity: Severity::Medium,
rule_id: "plc-insecure-protocol-port",
title: "Cleartext industrial protocol port".to_string(),
description: format!(
"POU `{pou}` opens `{callee}` on port {p}, a well-known cleartext OT \
protocol port with no built-in authentication or encryption."
),
cwe: Some("CWE-319"),
remediation: "Front the protocol with a secure gateway/VPN, or use the \
authenticated/encrypted variant; never expose it to untrusted \
networks.",
});
}
}
}
let _ = line;
}
/// The dotted/base identifier of an lvalue expression (`a`, `a.b` → `a.b`,
/// `a[i]` → `a`), for name-based rules.
fn flatten_ident(e: &Expr) -> Option<String> {
match e {
Expr::Ident(n, _) => Some(n.clone()),
Expr::Member { base, field, .. } => flatten_ident(base).map(|b| format!("{b}.{field}")),
Expr::Index { base, .. } => flatten_ident(base),
_ => None,
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::pipeline::plc::parser;
const VULN: &str = r#"
FUNCTION_BLOCK CommCtrl
VAR_INPUT
cmdIndex : INT;
END_VAR
VAR
Password : STRING := 'admin123';
buffer : ARRAY[0..15] OF INT;
Safety_Enable : BOOL := TRUE;
divisor : INT;
result : INT;
END_VAR
Safety_Enable := FALSE;
result := 100 / divisor;
buffer[cmdIndex] := 1;
Modbus_Connect(IP := '192.168.0.10', PORT := 502, AUTH := FALSE);
IF cmdIndex > 100 THEN
JMP fault;
END_IF;
fault:
result := 0;
END_FUNCTION_BLOCK
"#;
fn rule_ids(src: &str) -> Vec<&'static str> {
parser::parse(src)
.iter()
.flat_map(analyze)
.map(|h| h.rule_id)
.collect()
}
#[test]
fn vulnerable_program_triggers_every_rule() {
let ids = rule_ids(VULN);
for expected in [
"plc-hardcoded-credential",
"plc-default-password",
"plc-safety-bypass",
"plc-division-by-zero",
"plc-array-unchecked-index",
"plc-insecure-comm",
"plc-insecure-protocol-port",
"plc-unstructured-jump",
] {
assert!(
ids.contains(&expected),
"expected rule {expected}, got {ids:?}"
);
}
}
#[test]
fn clean_program_has_no_findings() {
let clean = r#"
PROGRAM Clean
VAR
a : INT := 5;
b : INT := 3;
total : INT;
END_VAR
IF b <> 0 THEN
total := a / b;
END_IF;
END_PROGRAM
"#;
assert!(rule_ids(clean).is_empty(), "clean program should be quiet");
}
}
-253
View File
@@ -1,253 +0,0 @@
//! Control-application dependency SBOM from a CODESYS `.projectarchive`.
//!
//! A `.projectarchive` is a ZIP that bundles the project plus its referenced
//! libraries and the target runtime. Each referenced library is an entry whose
//! path segment follows the CODESYS convention
//! `Name, Major.Minor.Patch.Build (Company)` (e.g. `Standard, 3.5.18.0 (System)`,
//! `CSV Utility SL, 1.9.0.0 (CODESYS)`); the runtime appears as a device-descriptor
//! entry `CODESYS Control … <version> …`. We enumerate those entries — no binary
//! parsing — and emit SBOM components tagged `pkg:codesys/…`, so the CVE pipeline
//! can match them (the runtime `Cmp*` / `3SLicense` components carry real CODESYS
//! CVEs).
use std::collections::BTreeSet;
use std::path::{Path, PathBuf};
use compliance_core::models::SbomEntry;
/// Collect the control-application SBOM from every `.projectarchive` reachable for
/// a target: the ingested artifact file itself (an uploaded archive), plus any
/// `*.projectarchive` committed inside the working tree — e.g. a git repo or an
/// extracted source archive that ships the archive alongside its PLCopen XML / ST
/// exports. Deduplicated by (name, version).
pub fn collect_sbom(artifact_file: &Path, working_path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let mut archives: Vec<PathBuf> = Vec::new();
if artifact_file.is_file() {
archives.push(artifact_file.to_path_buf());
}
for entry in walkdir::WalkDir::new(working_path)
.max_depth(8)
.into_iter()
.filter_map(|e| e.ok())
{
let p = entry.path();
if entry.file_type().is_file()
&& p.extension()
.and_then(|x| x.to_str())
.is_some_and(|x| x.eq_ignore_ascii_case("projectarchive"))
{
archives.push(p.to_path_buf());
}
}
let mut seen: BTreeSet<(String, String)> = BTreeSet::new();
let mut out = Vec::new();
for a in archives {
for e in projectarchive_sbom(&a, repo_id) {
if seen.insert((e.name.clone(), e.version.clone())) {
out.push(e);
}
}
}
out
}
/// Extract CODESYS library + runtime components from a `.projectarchive` (a zip).
/// Best-effort: returns empty if the file is not a readable zip (e.g. a bare
/// `.st`/`.xml` project, which carries no library manifest).
pub fn projectarchive_sbom(archive: &Path, repo_id: &str) -> Vec<SbomEntry> {
let Ok(file) = std::fs::File::open(archive) else {
return Vec::new();
};
let Ok(mut zip) = zip::ZipArchive::new(file) else {
return Vec::new();
};
let mut seen: BTreeSet<(String, String)> = BTreeSet::new();
let mut entries = Vec::new();
for i in 0..zip.len() {
let Ok(entry) = zip.by_index(i) else {
continue;
};
// Entry paths use `\` (Windows-authored) and/or `/` separators; the
// component id is one path segment.
for seg in entry.name().split(['/', '\\']) {
if let Some((name, version)) = parse_library(seg).or_else(|| parse_runtime(seg)) {
if seen.insert((name.clone(), version.clone())) {
let mut e = SbomEntry::new(
repo_id.to_string(),
name.clone(),
version.clone(),
"codesys".to_string(),
);
e.purl = Some(format!(
"pkg:codesys/{}@{version}",
name.replace(' ', "%20")
));
entries.push(e);
}
}
}
}
entries
}
/// `Name, X.Y.Z.W (Company)` → (name, version).
fn parse_library(seg: &str) -> Option<(String, String)> {
let seg = seg.trim();
// Company is the trailing "(…)".
let open = seg.rfind(" (")?;
let rest = &seg[open + 2..];
let close = rest.find(')')?;
if rest[..close].trim().is_empty() {
return None;
}
let head = seg[..open].trim(); // "Name, X.Y.Z.W"
let comma = head.rfind(", ")?;
let name = head[..comma].trim().to_string();
let version = head[comma + 2..].trim().to_string();
if name.is_empty() || !is_dotted_version(&version) {
return None;
}
Some((name, version))
}
/// Device-descriptor entry `CODESYS Control … X.Y.Z.W …` → (runtime name, version).
fn parse_runtime(seg: &str) -> Option<(String, String)> {
let seg = seg.trim();
if !seg.starts_with("CODESYS Control") {
return None;
}
let version = seg
.split_whitespace()
.find(|t| is_dotted_version(t))?
.to_string();
// The runtime name is the first field, before the run of padding spaces that
// precede the descriptor's numeric columns.
let name = seg.split(" ").next().unwrap_or(seg).trim().to_string();
if name.is_empty() {
return None;
}
Some((name, version))
}
/// A dotted numeric version with at least 3 components (`3.5.18.0`, `4.17.0.0`).
fn is_dotted_version(s: &str) -> bool {
let parts: Vec<&str> = s.split('.').collect();
parts.len() >= 3
&& parts
.iter()
.all(|p| !p.is_empty() && p.chars().all(|c| c.is_ascii_digit()))
}
#[cfg(test)]
mod tests {
use super::*;
use std::collections::HashMap;
use std::io::Write;
/// Build a synthetic `.projectarchive` (zip) mirroring the real CODESYS entry
/// naming (verified against Proemion/codesys-examples): a native `.project`,
/// referenced libraries as `Name, Version (Company)` segments, and a runtime
/// device descriptor.
fn synthetic_archive(dir: &Path) -> std::path::PathBuf {
let path = dir.join("App.projectarchive");
write_synthetic_archive(&path);
path
}
fn write_synthetic_archive(path: &Path) {
let file = std::fs::File::create(path).expect("create");
let mut zip = zip::ZipWriter::new(file);
let opts: zip::write::SimpleFileOptions = Default::default();
let names = [
"App.project",
r"{b0b5}\App.Device.Plc.compileinfo",
r"{e179}\Standard, 3.5.18.0 (System) standard.compiled-library-v3",
r"{e179}\Util, 3.5.21.0 (System) util.compiled-library-v3",
r"{e179}\CSV Utility SL, 1.9.0.0 (CODESYS) csv utility sl.compiled-library-v3",
r"{e179}\3SLicense, 3.5.20.0 (CODESYS) 3slicense.compiled-library-v3",
r"{0c63}\CODESYS Control for Linux ARM SL 0000 0006 4.17.0.0 4096 .zip",
];
for n in names {
zip.start_file(n, opts).expect("start");
zip.write_all(b"x").expect("write");
}
zip.finish().expect("finish");
}
#[test]
fn extracts_libraries_and_runtime_from_projectarchive() {
let tmp = std::env::temp_dir().join(format!("cs-plc-sbom-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&tmp).expect("mkdir");
let archive = synthetic_archive(&tmp);
let entries = projectarchive_sbom(&archive, "plc-target");
let by_name: HashMap<&str, &SbomEntry> =
entries.iter().map(|e| (e.name.as_str(), e)).collect();
// Libraries with their versions.
assert_eq!(
by_name.get("Standard").map(|e| e.version.as_str()),
Some("3.5.18.0")
);
assert_eq!(
by_name.get("Util").map(|e| e.version.as_str()),
Some("3.5.21.0")
);
assert_eq!(
by_name.get("CSV Utility SL").map(|e| e.version.as_str()),
Some("1.9.0.0"),
"multi-word library names must parse"
);
assert!(by_name.contains_key("3SLicense"));
// The runtime, from the device descriptor.
assert_eq!(
by_name
.get("CODESYS Control for Linux ARM SL")
.map(|e| e.version.as_str()),
Some("4.17.0.0")
);
// Every component is CODESYS-tagged with a purl the CVE pipeline can match,
// and the native `.project` / compileinfo are not mistaken for components.
for e in &entries {
assert_eq!(e.package_manager, "codesys");
assert!(e.purl.as_deref().unwrap_or("").starts_with("pkg:codesys/"));
}
assert!(!by_name.contains_key("App"));
let _ = std::fs::remove_dir_all(&tmp);
}
#[test]
fn collect_sbom_finds_a_projectarchive_committed_in_a_git_tree() {
let tmp = std::env::temp_dir().join(format!("cs-plc-collect-{}", uuid::Uuid::new_v4()));
let src = tmp.join("clone/src");
std::fs::create_dir_all(&src).expect("mkdir");
// Simulate a git clone that commits the archive alongside its exports.
write_synthetic_archive(&src.join("PumpStation.projectarchive"));
// The artifact "file" is a git URL (not a real file), so the SBOM must
// come from walking the cloned tree.
let entries = collect_sbom(Path::new("https://git.example/plc.git"), &tmp, "t");
let names: std::collections::HashSet<&str> =
entries.iter().map(|e| e.name.as_str()).collect();
assert!(
names.contains("Standard"),
"found libs in the committed archive"
);
assert!(names.contains("CODESYS Control for Linux ARM SL"));
let _ = std::fs::remove_dir_all(&tmp);
}
#[test]
fn non_zip_file_yields_no_sbom() {
let tmp = std::env::temp_dir().join(format!("cs-plc-sbom-st-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&tmp).expect("mkdir");
let st = tmp.join("prog.st");
std::fs::write(&st, "PROGRAM P\nVAR x : INT; END_VAR\nEND_PROGRAM\n").expect("write");
assert!(projectarchive_sbom(&st, "t").is_empty());
let _ = std::fs::remove_dir_all(&tmp);
}
}
-3
View File
@@ -202,9 +202,6 @@ pub enum PlcFormat {
PlcopenXml,
/// IEC 61131-3 Structured Text source.
StructuredText,
/// A CODESYS project archive (`.projectarchive` — a zip bundling the project
/// plus its referenced libraries and runtime; the source of the control-app SBOM).
ProjectArchive,
}
/// PLC-specific configuration for a [`ArtifactKind::PlcProject`] artifact.
-5
View File
@@ -24,9 +24,6 @@ pub enum ScanType {
MobileStatic,
/// Static analysis of a container image.
ContainerScan,
/// Dynamic probing of a running PLC/SPS device over industrial protocols
/// (Modbus/TCP, OPC UA, …) for exposed/unauthenticated control access.
IcsProbe,
}
impl std::fmt::Display for ScanType {
@@ -46,7 +43,6 @@ impl std::fmt::Display for ScanType {
Self::PlcControlLogic => write!(f, "plc_control_logic"),
Self::MobileStatic => write!(f, "mobile_static"),
Self::ContainerScan => write!(f, "container_scan"),
Self::IcsProbe => write!(f, "ics_probe"),
}
}
}
@@ -80,7 +76,6 @@ pub enum ScanPhase {
LlmTriage,
IssueCreation,
DastScanning,
IcsProbe,
Completed,
}
+13 -190
View File
@@ -14,12 +14,8 @@ use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
pub enum ArtifactRequirement {
/// Source code — a git repo or a source archive.
Code,
/// A reachable running instance (any live URL / endpoint, scheme-agnostic —
/// e.g. the ICS probe works off the host:port of a modbus:// or http:// ref).
/// A reachable running instance (live URL / endpoint).
RunningUrl,
/// A reachable **web** endpoint — a live URL with an http(s) scheme. DAST is
/// an HTTP crawler, so a modbus:// / opc.tcp:// endpoint does not satisfy it.
HttpUrl,
/// A firmware image / binary blob.
Firmware,
/// A PLC project (PLCopen XML or Structured Text).
@@ -138,7 +134,7 @@ fn sast_umbrella() -> Vec<ScanRule> {
/// The rule set for a target type. Scans that are never applicable to a type are
/// simply absent (e.g. DAST is not listed for a PLC target).
pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
use ArtifactRequirement::{Firmware, HttpUrl, Mobile, Plc, RunningUrl};
use ArtifactRequirement::{Firmware, Mobile, Plc, RunningUrl};
match target_type {
TargetType::WebApp | TargetType::BackendService => {
let mut r = sast_umbrella();
@@ -146,7 +142,7 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
true,
"Dynamic scan of the running endpoint",
HttpUrl,
RunningUrl,
));
r
}
@@ -207,62 +203,16 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
false,
"Dynamic scan of exposed network services (if any)",
HttpUrl,
RunningUrl,
));
r
}
TargetType::PlcSps => {
// A PLC/SPS device is a composite: the control application *and* the
// device it runs on (firmware/OS + reachable runtime services). The
// control-logic scan runs on the PLC project; the firmware and DAST
// scans light up only when a firmware image / running endpoint is
// attached (e.g. a CODESYS runtime on a Yocto image with WebVisu).
// Firmware-image SBOM/CVE *execution* is shared with the firmware
// families and tracked in #151/#128; DAST over a WebVisu/OPC-UA
// endpoint uses the existing DAST path.
vec![
ScanRule::new(
TargetType::PlcSps => vec![ScanRule::new(
ScanType::PlcControlLogic,
true,
"Control-logic security rules over the PLC program",
Plc,
),
// Device-level scans are offered but opt-in (default-off): they
// apply only when a firmware image is attached, and firmware-image
// SBOM/CVE *execution* is shared with the firmware families and
// still landing (#151/#128), so they must not silently auto-run.
ScanRule::new(
ScanType::FirmwareStatic,
false,
"Static analysis of the device firmware image (OS + runtime)",
Firmware,
),
ScanRule::new(
ScanType::Sbom,
false,
"SBOM from the device firmware image (OS packages + CODESYS runtime)",
Firmware,
),
ScanRule::new(
ScanType::Cve,
false,
"Match device firmware components against known CVEs",
Firmware,
),
ScanRule::new(
ScanType::Dast,
false,
"Dynamic scan of the running device (WebVisu / exposed services)",
HttpUrl,
),
ScanRule::new(
ScanType::IcsProbe,
false,
"Probe the running device over industrial protocols (Modbus/TCP, …)",
RunningUrl,
),
]
}
)],
}
}
@@ -279,9 +229,6 @@ pub fn supports_pentest(target_type: TargetType) -> bool {
| TargetType::AndroidApp
| TargetType::IosApp
| TargetType::EmbeddedLinuxYocto
// A PLC/SPS device exposes reachable runtime services (WebVisu, OPC UA,
// the CODESYS programming protocol), so an active pentest applies.
| TargetType::PlcSps
)
}
@@ -289,9 +236,7 @@ pub fn supports_pentest(target_type: TargetType) -> bool {
fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
match req {
ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
ArtifactRequirement::RunningUrl | ArtifactRequirement::HttpUrl => {
Some(ArtifactKind::LiveUrl)
}
ArtifactRequirement::RunningUrl => Some(ArtifactKind::LiveUrl),
ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
@@ -300,29 +245,13 @@ fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
}
}
/// Whether a live-URL reference is an http(s) web endpoint (vs. an industrial
/// endpoint like `modbus://` / `opc.tcp://`, which DAST cannot crawl).
fn is_http_url(source_ref: &str) -> bool {
let s = source_ref.trim();
s.starts_with("http://") || s.starts_with("https://")
}
/// Whether the target carries an artifact that satisfies the requirement.
fn requirement_satisfied(req: ArtifactRequirement, target: &OnboardedTarget) -> bool {
match req {
ArtifactRequirement::Code => target.code_artifact().is_some(),
ArtifactRequirement::RunningUrl => target.has(ArtifactKind::LiveUrl),
ArtifactRequirement::HttpUrl => target
.artifacts
.iter()
.any(|a| a.kind == ArtifactKind::LiveUrl && is_http_url(&a.source_ref)),
ArtifactRequirement::Firmware => target.has(ArtifactKind::FirmwareImage),
// A PLC project artifact, or a code artifact (git repo / source archive)
// holding the control logic as PLCopen XML / ST exports — the common way
// CODESYS projects are version-controlled.
ArtifactRequirement::Plc => {
target.has(ArtifactKind::PlcProject) || target.code_artifact().is_some()
}
ArtifactRequirement::Plc => target.has(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => target.has(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => target.has(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => true,
@@ -339,10 +268,6 @@ pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
let required_artifact = representative_kind(rule.requires);
let blocked_reason = if satisfied {
None
} else if rule.requires == ArtifactRequirement::HttpUrl {
// A live URL may be present but non-HTTP (e.g. modbus://): be
// specific so the user knows DAST needs a web endpoint.
Some("no http(s) live URL — DAST needs a web endpoint".to_string())
} else {
Some(match required_artifact {
Some(kind) => format!("no {kind} artifact provided"),
@@ -415,124 +340,22 @@ mod tests {
}
#[test]
fn plc_control_logic_is_default_on_and_device_scans_block_without_artifacts() {
// A PLC project alone: control-logic runs; the device-level scans are
// offered but blocked until a firmware image / running endpoint is added.
fn plc_offers_only_control_logic() {
let t = target_with(
TargetType::PlcSps,
vec![Artifact::plc_project("p.xml", PlcFormat::PlcopenXml)],
);
let opts = applicable_scans(&t);
let plc = option(&opts, ScanType::PlcControlLogic).expect("control-logic offered");
assert!(plc.default_on && plc.blocked_reason.is_none());
for scan in [ScanType::FirmwareStatic, ScanType::Sbom, ScanType::Cve] {
let o = option(&opts, scan).expect("device scan offered");
assert!(
!o.default_on,
"{scan} must not pre-select without a firmware image"
);
assert!(o.blocked_reason.is_some());
}
let dast = option(&opts, ScanType::Dast).expect("dast offered");
assert!(!dast.default_on);
assert!(dast.blocked_reason.is_some());
}
#[test]
fn plc_control_logic_is_satisfied_by_a_git_repo() {
// A CODESYS project version-controlled in git (PLCopen XML / ST exports),
// no uploaded PlcProject artifact.
let t = target_with(TargetType::PlcSps, vec![Artifact::git_repo("u", "main")]);
let opts = applicable_scans(&t);
let plc = option(&opts, ScanType::PlcControlLogic).expect("control-logic offered");
assert!(
plc.default_on && plc.blocked_reason.is_none(),
"a git repo should satisfy PLC control-logic"
);
}
#[test]
fn plc_composite_lights_up_device_scans_with_firmware_and_url() {
// A CODESYS-on-Yocto device: PLC project + firmware image + WebVisu URL.
let t = target_with(
TargetType::PlcSps,
vec![
Artifact::plc_project("p.xml", PlcFormat::PlcopenXml),
Artifact::firmware_image("device.img"),
Artifact::live_url("http://plc.local/webvisu"),
],
);
let opts = applicable_scans(&t);
for scan in [
ScanType::PlcControlLogic,
ScanType::FirmwareStatic,
ScanType::Sbom,
ScanType::Cve,
] {
let o = option(&opts, scan).expect("scan offered");
assert!(o.blocked_reason.is_none(), "{scan} should be unblocked");
}
// Control-logic auto-runs; the device-level scans are unblocked but opt-in
// (default-off) until firmware-image execution lands (#151/#128).
assert!(option(&opts, ScanType::PlcControlLogic).unwrap().default_on);
assert!(!option(&opts, ScanType::Sbom).unwrap().default_on);
assert!(!option(&opts, ScanType::Dast).unwrap().default_on);
assert!(option(&opts, ScanType::Dast)
.unwrap()
.blocked_reason
.is_none());
}
#[test]
fn plc_with_modbus_url_offers_ics_probe_but_blocks_dast() {
// A soft-PLC reachable only over Modbus/TCP (no WebVisu). The ICS probe
// is applicable (it works off host:port), but DAST — an HTTP crawler —
// must be blocked so it isn't offered/run against a non-web endpoint.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("modbus://plc-sim:502")],
);
let opts = applicable_scans(&t);
let ics = option(&opts, ScanType::IcsProbe).expect("ics probe offered");
assert!(
ics.blocked_reason.is_none(),
"ICS probe should be unblocked for a modbus:// endpoint"
);
assert!(!ics.default_on, "ICS probe stays opt-in (default-off)");
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(
dast.blocked_reason.is_some(),
"DAST must be blocked without an http(s) endpoint"
);
assert!(!dast.default_on);
}
#[test]
fn plc_with_http_webvisu_offers_both_dast_and_ics_probe() {
// A PLC exposing a WebVisu over HTTP: both DAST (web) and the ICS probe
// (OT ports on the same host) are applicable.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("http://plc.local/webvisu")],
);
let opts = applicable_scans(&t);
assert!(option(&opts, ScanType::Dast)
.expect("dast offered")
.blocked_reason
.is_none());
assert!(option(&opts, ScanType::IcsProbe)
.expect("ics probe offered")
.blocked_reason
.is_none());
assert_eq!(opts.len(), 1);
assert_eq!(opts[0].scan, ScanType::PlcControlLogic);
assert!(opts[0].default_on);
}
#[test]
fn pentest_support_matches_reachable_families() {
assert!(supports_pentest(TargetType::WebApp));
assert!(supports_pentest(TargetType::BackendService));
assert!(supports_pentest(TargetType::EmbeddedLinuxYocto));
// A PLC/SPS device is network-reachable (WebVisu / OPC UA / 11740).
assert!(supports_pentest(TargetType::PlcSps));
assert!(!supports_pentest(TargetType::PlcSps));
assert!(!supports_pentest(TargetType::FirmwareBareMetal));
assert!(!supports_pentest(TargetType::DesktopApp));
}
@@ -78,16 +78,8 @@ pub fn validate_artifact_ref(kind: &str, source_ref: &str) -> Option<String> {
.then(|| "Enter a git URL — https://…, ssh://…, or git@host:path".to_string())
}
"live_url" => {
// http(s) for web/DAST targets; modbus:// and opc.tcp:// for ICS
// devices probed by the ICS probe (e.g. modbus://plc:502).
let ok = (s.starts_with("https://")
|| s.starts_with("http://")
|| s.starts_with("modbus://")
|| s.starts_with("opc.tcp://"))
&& no_space;
(!ok).then(|| {
"Enter a URL — https://app.example.com, or modbus://host:502 for a PLC".to_string()
})
let ok = (s.starts_with("https://") || s.starts_with("http://")) && no_space;
(!ok).then(|| "Enter an http(s) URL, e.g. https://app.example.com".to_string())
}
"container_image" => {
(!no_space).then(|| "Enter an image ref, e.g. registry/name:tag".to_string())
@@ -138,37 +130,6 @@ pub async fn create_target(
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Upload a file artifact (PLC project, firmware image, source archive, mobile
/// package) to a target — proxied to the agent as multipart.
#[server]
pub async fn upload_target_artifact(
id: String,
kind: String,
plc_format: Option<String>,
filename: String,
bytes: Vec<u8>,
) -> Result<TargetResponse, ServerFnError> {
let mut form = reqwest::multipart::Form::new().text("kind", kind).part(
"file",
reqwest::multipart::Part::bytes(bytes).file_name(filename),
);
if let Some(pf) = plc_format {
form = form.text("plc_format", pf);
}
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/targets/{id}/artifacts/upload"),
)
.await?
.multipart(form)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Update a target's name / type / artifacts (dashboard editor).
#[server]
pub async fn update_target(
@@ -204,28 +165,6 @@ pub async fn update_target(
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Enable specific opt-in scans on a target by setting `scan_config.enabled_scans`.
/// `scans` are serde scan-type names (lowercase, no underscores — e.g. `icsprobe`).
#[server]
pub async fn enable_target_scans(
id: String,
scans: Vec<String>,
) -> Result<TargetResponse, ServerFnError> {
let body = serde_json::json!({ "scan_config": { "enabled_scans": scans } });
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/targets/{id}"),
)
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Run kind-based classification on a target.
#[server]
pub async fn detect_target(id: String) -> Result<TargetResponse, ServerFnError> {
@@ -1,4 +1,3 @@
use axum::extract::DefaultBodyLimit;
use axum::routing::{get, post};
use axum::{middleware, Extension};
use dioxus::prelude::*;
@@ -67,9 +66,6 @@ pub fn server_start(app: fn() -> Element) -> Result<(), DashboardError> {
// Webhook proxy: forward to agent (no auth required)
.route("/webhook/{platform}/{repo_id}", post(webhook_proxy))
.serve_dioxus_application(ServeConfig::new(), app)
// Allow large artifact uploads through the upload server function
// (PLC .projectarchive, firmware, mobile) — default is 2 MiB.
.layer(DefaultBodyLimit::max(512 * 1024 * 1024))
.layer(Extension(PendingOAuthStore::default()))
.layer(middleware::from_fn(require_auth))
.layer(Extension(server_state))
+4 -239
View File
@@ -2,8 +2,8 @@ use dioxus::prelude::*;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::{
create_target, detect_target, enable_target_scans, fetch_applicable_scans, trigger_target_scan,
upload_target_artifact, validate_artifact_ref, validate_target_name, ArtifactInputDto,
create_target, detect_target, fetch_applicable_scans, trigger_target_scan,
validate_artifact_ref, validate_target_name, ArtifactInputDto,
};
/// (value, label, one-line description) for the 9 target families.
@@ -41,23 +41,6 @@ const ARTIFACT_KINDS: &[(&str, &str)] = &[
const STEP_LABELS: &[&str] = &["Target type", "Artifacts", "Review", "Done"];
/// Artifact kinds provided as an uploaded file (rather than a URL/text ref).
fn is_file_kind(kind: &str) -> bool {
matches!(
kind,
"plc_project" | "firmware_image" | "source_archive" | "mobile_package"
)
}
/// A file artifact staged in the wizard, uploaded after the target is created.
#[derive(Clone, PartialEq)]
struct PendingFile {
kind: String,
plc_format: Option<String>,
filename: String,
bytes: Vec<u8>,
}
/// One row in the applicable-scans list on the success step.
#[component]
fn ScanRow(scan: serde_json::Value) -> Element {
@@ -125,10 +108,6 @@ pub fn OnboardingPage() -> Element {
let mut new_kind = use_signal(|| "git_repo".to_string());
let mut new_source = use_signal(String::new);
let mut new_branch = use_signal(|| "main".to_string());
// File-upload artifacts (PLC project, firmware image, ...).
let mut new_plc_format = use_signal(|| "plcopen_xml".to_string());
let mut new_file = use_signal(|| Option::<(String, Vec<u8>)>::None);
let mut pending_files = use_signal(Vec::<PendingFile>::new);
// Create + result state.
let mut creating = use_signal(|| false);
@@ -137,35 +116,11 @@ pub fn OnboardingPage() -> Element {
let mut suggested = use_signal(|| Option::<String>::None);
let mut created_id = use_signal(|| Option::<String>::None);
let mut scan_msg = use_signal(|| Option::<String>::None);
// Opt-in scans (default-off but unblocked) the user ticks to enable before
// running — stored as serde scan-type names (lowercase, no underscores).
let mut enabled_extra = use_signal(Vec::<String>::new);
let step_now = step();
let name_error = validate_target_name(&name());
let can_advance_type = name_error.is_none() && !target_type().trim().is_empty();
let has_artifacts = !artifacts().is_empty() || !pending_files().is_empty();
// Opt-in scans: applicable + unblocked, but default-off (e.g. the ICS probe).
// The user ticks these to enable them before the first run. Each entry is
// (display name for the label, serde scan-type name for the enable call —
// lowercase, no underscores, matching ScanType's rename_all = "lowercase").
let optin_scans: Vec<(String, String)> = scans()
.iter()
.filter_map(|s| {
let unblocked = s.get("blocked_reason").and_then(|v| v.as_str()).is_none();
let default_on = s
.get("default_on")
.and_then(|v| v.as_bool())
.unwrap_or(false);
if unblocked && !default_on {
let display = s.get("scan").and_then(|v| v.as_str())?.to_string();
let serde_name = display.replace('_', "");
Some((display, serde_name))
} else {
None
}
})
.collect();
let has_artifacts = !artifacts().is_empty();
// Live validation of the artifact reference being typed (empty = no error yet).
let new_source_error = if new_source().is_empty() {
None
@@ -238,36 +193,6 @@ pub fn OnboardingPage() -> Element {
// ---- Step 1: artifacts ----
if step_now == 1 {
div { class: "card-header", "Attach artifacts" }
if target_type() == "plc_sps" {
div {
style: "margin: 12px 16px 0; padding: 12px 14px; border-left: 3px solid var(--accent, #3b82f6); background: var(--surface-2, rgba(59,130,246,0.08)); font-size: 0.88em; line-height: 1.55;",
div { style: "font-weight: 600; margin-bottom: 4px;", "CODESYS / PLC projects" }
"Attach a "
b { "PLC project" }
" (PLCopen XML / ST, or a .projectarchive), or a "
b { "Git repository" }
" of exported source — every scan is then just a pull."
ul { style: "margin: 6px 0 0; padding-left: 18px;",
li {
b { "Control-logic SAST" }
" — commit "
b { "PLCopen XML exports" }
" (Project → Export PLCopenXML) or raw .st; ST and graphical FBD/LD are both analyzed."
}
li {
b { "Library + runtime SBOM" }
" — include the "
b { ".projectarchive" }
"; PLCopen XML alone carries no libraries."
}
li {
"Avoid committing only the binary "
code { ".project" }
" — it can't be parsed and doesn't diff."
}
}
}
}
div { style: "padding: 16px;",
div { style: "display: flex; gap: 8px; flex-wrap: wrap; align-items: flex-end;",
div { class: "form-group", style: "margin: 0;",
@@ -280,78 +205,6 @@ pub fn OnboardingPage() -> Element {
}
}
}
if is_file_kind(&new_kind()) {
div { class: "form-group", style: "margin: 0; flex: 1; min-width: 240px;",
label { "File" }
input {
r#type: "file",
onchange: move |evt| {
let Some(file) = evt.files().into_iter().next() else { return; };
let name = file.name();
// Auto-detect the PLC format from the file extension.
let lname = name.to_ascii_lowercase();
if lname.ends_with(".projectarchive") || lname.ends_with(".project") {
new_plc_format.set("project_archive".to_string());
} else if lname.ends_with(".xml") || lname.ends_with(".plcopen") {
new_plc_format.set("plcopen_xml".to_string());
} else if lname.ends_with(".st") || lname.ends_with(".exp") || lname.ends_with(".scl") {
new_plc_format.set("structured_text".to_string());
}
spawn(async move {
if let Ok(bytes) = file.read_bytes().await {
new_file.set(Some((name, bytes.to_vec())));
}
});
},
}
}
if new_kind() == "plc_project" {
div { class: "form-group", style: "margin: 0;",
label { "Format" }
select {
value: "{new_plc_format}",
oninput: move |e| new_plc_format.set(e.value()),
option {
value: "plcopen_xml",
selected: new_plc_format() == "plcopen_xml",
"PLCopen XML",
}
option {
value: "structured_text",
selected: new_plc_format() == "structured_text",
"Structured Text",
}
option {
value: "project_archive",
selected: new_plc_format() == "project_archive",
"Project archive (.projectarchive)",
}
}
}
}
button {
class: "btn btn-secondary",
disabled: new_file().is_none(),
onclick: move |_| {
if let Some((fname, data)) = new_file() {
let kind = new_kind();
let plc_format = if kind == "plc_project" {
Some(new_plc_format())
} else {
None
};
pending_files.write().push(PendingFile {
kind,
plc_format,
filename: fname,
bytes: data,
});
new_file.set(None);
}
},
"+ Add file"
}
} else {
div { class: "form-group", style: "margin: 0; flex: 1; min-width: 240px;",
label { "Reference (URL / path / text)" }
input {
@@ -392,31 +245,9 @@ pub fn OnboardingPage() -> Element {
"+ Add"
}
}
}
if is_file_kind(&new_kind()) {
if let Some((fname, data)) = new_file() {
div { style: "font-size: 0.85em; opacity: 0.7; margin-top: 6px;",
"Selected: {fname} ({data.len()} bytes)"
}
}
} else if let Some(err) = new_source_error.clone() {
if let Some(err) = new_source_error.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em; margin-top: 6px;", "{err}" }
}
// Staged file artifacts (uploaded after the target is created).
for (i, pf) in pending_files().iter().enumerate() {
div {
style: "display: flex; justify-content: space-between; align-items: center; padding: 8px 12px; border: 1px solid var(--border, #333); border-radius: 6px; margin-top: 6px;",
span {
span { style: "opacity: 0.7;", "{kind_label(&pf.kind)} (file): " }
"{pf.filename} ({pf.bytes.len()} bytes)"
}
button {
class: "btn btn-ghost-danger btn-sm",
onclick: move |_| { pending_files.write().remove(i); },
"Remove"
}
}
}
div { style: "margin-top: 16px;",
if has_artifacts {
@@ -480,39 +311,6 @@ pub fn OnboardingPage() -> Element {
ScanRow { scan: s }
}
}
if !optin_scans.is_empty() {
div { style: "margin-top: 12px; padding: 10px; border: 1px dashed var(--border, #ccc); border-radius: 6px;",
div { style: "font-weight: 600; margin-bottom: 6px;", "Enable opt-in scans" }
div { style: "opacity: 0.7; font-size: 0.85em; margin-bottom: 8px;",
"These are applicable but off by default (they touch a live device). Tick to enable before running."
}
for pair in optin_scans.clone() {
{
let (display, serde_name) = pair;
let cb_name = serde_name.clone();
rsx! {
label {
style: "display: flex; gap: 6px; align-items: center; margin-top: 4px;",
input {
r#type: "checkbox",
checked: enabled_extra().contains(&serde_name),
onchange: move |_| {
let mut v = enabled_extra();
if let Some(p) = v.iter().position(|x| x == &cb_name) {
v.remove(p);
} else {
v.push(cb_name.clone());
}
enabled_extra.set(v);
},
}
"Enable {display}"
}
}
}
}
}
}
if let Some(msg) = scan_msg() {
div { style: "margin-top: 8px; color: var(--success, #2a2);", "{msg}" }
}
@@ -521,21 +319,8 @@ pub fn OnboardingPage() -> Element {
class: "btn btn-primary",
onclick: move |_| {
if let Some(id) = created_id() {
let extra = enabled_extra();
scan_msg.set(Some("Scan triggered...".to_string()));
spawn(async move {
// Persist any ticked opt-in scans first, so the
// agent's build_scan_plan includes them this run.
if !extra.is_empty() {
if let Err(e) =
enable_target_scans(id.clone(), extra).await
{
scan_msg.set(Some(format!(
"Failed to enable opt-in scans: {e}"
)));
return;
}
}
match trigger_target_scan(id).await {
Ok(_) => scan_msg.set(Some(
"Scan started — findings will appear as it runs.".to_string(),
@@ -555,8 +340,6 @@ pub fn OnboardingPage() -> Element {
target_type.set(String::new());
description.set(String::new());
artifacts.write().clear();
pending_files.write().clear();
new_file.set(None);
scans.write().clear();
suggested.set(None);
created_id.set(None);
@@ -595,7 +378,6 @@ pub fn OnboardingPage() -> Element {
let tt = target_type();
let desc = description();
let arts = artifacts();
let files = pending_files();
let d = if desc.trim().is_empty() { None } else { Some(desc) };
creating.set(true);
error.set(None);
@@ -610,23 +392,6 @@ pub fn OnboardingPage() -> Element {
.map(String::from);
if let Some(id) = id {
created_id.set(Some(id.clone()));
// Upload staged file artifacts now that the target exists.
for pf in files {
let fname = pf.filename.clone();
if let Err(e) = upload_target_artifact(
id.clone(),
pf.kind,
pf.plc_format,
pf.filename,
pf.bytes,
)
.await
{
error.set(Some(format!(
"Upload failed for {fname}: {e}"
)));
}
}
if let Ok(sc) = fetch_applicable_scans(id.clone()).await {
scans.set(sc.data.scans);
}
+2 -2
View File
@@ -232,7 +232,7 @@ pub fn TargetsPage() -> Element {
value: "{edit_type}",
oninput: move |e| edit_type.set(e.value()),
for (v, l) in TARGET_TYPES.iter().copied() {
option { value: "{v}", selected: edit_type() == v, "{l}" }
option { value: "{v}", "{l}" }
}
}
}
@@ -257,7 +257,7 @@ pub fn TargetsPage() -> Element {
value: "{e_kind}",
oninput: move |e| e_kind.set(e.value()),
for (v, l) in ARTIFACT_KINDS.iter().copied() {
option { value: "{v}", selected: e_kind() == v, "{l}" }
option { value: "{v}", "{l}" }
}
}
}
-2
View File
@@ -20,7 +20,6 @@ export default withMermaid(defineConfig({
{ text: 'Getting Started', link: '/guide/getting-started' },
{ text: 'Adding Repositories', link: '/guide/repositories' },
{ text: 'Running Scans', link: '/guide/scanning' },
{ text: 'PLC / SPS (CODESYS)', link: '/guide/plc' },
{ text: 'Understanding Findings', link: '/guide/findings' },
{ text: 'SBOM & Licenses', link: '/guide/sbom' },
{ text: 'Issues & Tracking', link: '/guide/issues' },
@@ -44,7 +43,6 @@ export default withMermaid(defineConfig({
items: [
{ text: 'Glossary', link: '/reference/glossary' },
{ text: 'Tools & Scanners', link: '/reference/tools' },
{ text: 'PLC Runtime Landscape', link: '/reference/plc-runtimes' },
],
},
],
-97
View File
@@ -1,97 +0,0 @@
# PLC / SPS Projects (CODESYS)
Certifai analyzes industrial control logic (IEC 61131-3) for PLC/SPS targets such
as CODESYS projects. A single PLC/SPS target is treated as a **composite device**:
the control application *and* the device it runs on.
| What you provide | What Certifai does |
| --- | --- |
| PLC project (PLCopen XML / ST, or a `.projectarchive`) | **Control-logic SAST** — semantic security rules over ST **and** graphical FBD/LD |
| A `.projectarchive` | **Control-app SBOM** — the referenced CODESYS libraries + the runtime version, matched against known CVEs |
| A device firmware image | Firmware SBOM / CVE (opt-in) |
| A reachable endpoint (WebVisu, OPC UA) | DAST / pentest (opt-in) |
## Two ways to deliver the project
You can either **upload** the project when onboarding, or point Certifai at a
**git repository** (recommended — every scan is just a `git pull`, no re-upload).
### Option A — Upload
On the onboarding wizard, choose target type **PLC / SPS**, then attach a **PLC
project** artifact and pick its format:
- **PLCopen XML** (`.xml`) — export from CODESYS via *Project → Export PLCopenXML*.
- **Structured Text** (`.st`) — a raw ST file.
- **Project archive** (`.projectarchive`) — *File → Project Archive → Save/Send
Archive…* with **"Referenced libraries"** ticked. This is the only form that
also yields the **library + runtime SBOM**.
### Option B — Git repository (recommended)
Attach a **Git repository** artifact to the PLC/SPS target. Certifai clones it and
runs the control-logic scan over the exported source in the repo.
## Best-case git repository layout
Because the binary `.project` does not diff or merge in git, commit **textual
exports** for review-friendly SAST, and include the **`.projectarchive`** so the
library/runtime SBOM is available too:
```text
my-plc-project/
├── src/
│ ├── PLC_PRG.xml # PLCopen XML export (ST or FBD/LD) — one per POU
│ ├── PumpController.xml
│ ├── SafetyInterlock.xml
│ └── GVL.xml # global variable lists, also as PLCopen XML
├── PumpStation.projectarchive # optional but recommended → library + runtime SBOM
└── README.md
```
**Guidelines**
- **Export to PLCopen XML** (`Project → Export PLCopenXML`), one file per POU, and
commit those. ST, **and graphical FBD/LD**, are both analyzed.
- Alternatively commit raw `.st` / `.exp` / `.scl` files — also analyzed.
- **Do not** commit only the binary `.project` — it cannot be parsed (and does not
diff). If you want the library SBOM, commit the **`.projectarchive`** as well.
- CODESYS's built-in Git integration, which stores an exported representation,
works too — as long as the committed form is PLCopen XML / textual.
::: tip What unlocks what
- **Control-logic SAST** needs textual source in the repo (PLCopen XML or `.st`).
- **Library + runtime SBOM** needs a **`.projectarchive`** — PLCopen XML exports do
**not** carry the referenced libraries.
:::
## What the scanner finds
The control-logic rules are CWE-mapped and include: hardcoded credentials
(CWE-798), default/weak passwords (CWE-1393), safety interlock / watchdog bypass
(CWE-1384), unchecked array indexing (CWE-129), division-by-zero (CWE-369,
guard-aware), cleartext/insecure communication (CWE-319), insecure protocol ports
(CWE-319, e.g. Modbus 502, FTP 21, Telnet 23), and unstructured jumps (CWE-691).
The **SBOM** view lists the CODESYS libraries (`pkg:codesys/<name>@<version>`) and
the runtime; matching runtime components (e.g. the `Cmp*` / `3SLicense` libraries)
surface real CODESYS advisories as CVE alerts.
## Dynamic testing — ICS protocol probe
Beyond the static analysis, Certifai can **probe the running device** over
industrial protocols. Attach a **Live URL** artifact (the device host / WebVisu
URL) to the PLC/SPS target and enable the **ICS Probe** scan.
The probe is **read-only** — it never writes to the live process. It currently
speaks **Modbus/TCP** (port 502): it confirms whether the device answers
unauthenticated Modbus requests and reads its device identity (vendor / product /
revision). Because Modbus/TCP has no authentication or encryption in the protocol,
a reachable endpoint that answers is reported as an exposed control interface
(CWE-306). OPC UA and EtherNet/IP probes are planned.
::: warning
The ICS probe connects to the live device. It is **opt-in** (off by default) and
should only be run against targets you are authorized to test. It performs reads
only, never writes.
:::
-97
View File
@@ -1,97 +0,0 @@
# PLC Runtime Landscape & Support
A soft PLC is a **SoC + Linux + a software runtime + an IEC 61131-3 control app**
(see [PLC / SPS Projects](/guide/plc)).
The **runtime** is what defines the device — it provides the IEC engine, the
Modbus / OPC UA / EtherNet/IP servers, and the WebVisu. This page tracks the
runtime ecosystems Certifai may encounter.
We do **not** aim to support every runtime up front. Certifai supports the
**CODESYS family** today; everything else is a **watch-list** — when a customer
shows up using one, we add the parser/support for it then. The dynamic OT probe
(Modbus / OPC UA / EtherNet/IP) is **vendor-agnostic** and works regardless of
the runtime.
## Support status
| Status | Meaning |
| --- | --- |
| ✅ **Supported** | Static analysis works today (control-logic SAST + library/runtime SBOM + CVE). |
| 🟡 **Covered via CODESYS** | A rebranded CODESYS runtime — our CODESYS parsing applies (may need minor per-vendor tweaks). |
| 🔭 **Watch-list** | Own project format — we add a format parser when a customer needs it. The dynamic OT probe already applies. |
| 🧪 **Test-bench** | A free runtime we use to *reconstruct and dynamically test* a device (see epic: provision-and-test). |
## 1. CODESYS and rebranded CODESYS (the largest slice)
Much of the market licenses the CODESYS runtime and rebrands the IDE. If a
customer "doesn't use CODESYS", they often do — under another name.
| Product / vendor | Based on | Status |
| --- | --- | --- |
| **CODESYS** (3S-Smart Software Solutions) | CODESYS | ✅ Supported |
| Schneider **EcoStruxure Machine Expert** (ex-SoMachine) | CODESYS | 🟡 Covered via CODESYS |
| **WAGO** e!COCKPIT / PFC controllers | CODESYS | 🟡 Covered via CODESYS |
| **ABB** AC500 / Automation Builder | CODESYS | 🟡 Covered via CODESYS |
| **Bosch Rexroth** ctrlX / IndraLogic | CODESYS | 🟡 Covered via CODESYS |
| **Eaton** XSoft-CODESYS, **KEBA** KeStudio, Berghof, Kontron, Festo (CPX-E), IFM, Turck, … | CODESYS | 🟡 Covered via CODESYS |
## 2. Other embeddable IEC 61131-3 runtime toolkits
Same model as CODESYS (an OEM licenses a runtime + IDE and bakes it into a
device), but with **different project formats and libraries**.
| Toolkit | Vendor | Status |
| --- | --- | --- |
| **ProConOS / MULTIPROG** | Phoenix Contact / KW-Software | 🔭 Watch-list |
| **ISaGRAF** (also does IEC 61499) | Rockwell | 🔭 Watch-list |
| **straton** | COPA-DATA | 🔭 Watch-list |
| **logi.CAD** | logi.cals | 🔭 Watch-list |
## 3. Fully proprietary ecosystems (own runtime + IDE + protocols)
Static analysis here needs a **per-vendor project parser**; the **dynamic OT
probe still works** (they speak Modbus / OPC UA / EtherNet/IP, plus vendor
protocols like S7comm / CIP).
| Ecosystem | Vendor | Notes | Status |
| --- | --- | --- | --- |
| **TIA Portal / STEP 7** (S7-1200/1500), S7-1500 **Software Controller**, **Virtual PLC** | Siemens | Largest install base; the soft/virtual variants are Linux/container | 🔭 Watch-list |
| **Studio 5000** (ControlLogix / CompactLogix) | Rockwell / Allen-Bradley | Strong in North America | 🔭 Watch-list |
| **TwinCAT 3** | Beckhoff | Genuine PC-based control on Windows / TwinCAT-BSD; IEC 61131-3 **+ C++ + Simulink** | 🔭 Watch-list |
| **Automation Studio** | B&R (ABB) | Own Automation Runtime | 🔭 Watch-list |
| **GX Works** (MELSEC) | Mitsubishi | | 🔭 Watch-list |
| **Sysmac Studio** (NX / NJ) | Omron | | 🔭 Watch-list |
| **Proficy Machine Edition** (PACSystems) | Emerson / GE | | 🔭 Watch-list |
## 4. Linux-native / containerized soft-PLC (the direction of travel)
| Product | Vendor | Notes | Status |
| --- | --- | --- | --- |
| **PLCnext** | Phoenix Contact | Open, Linux-based; native runtime is eCLR (not CODESYS), but can also run CODESYS as an app | 🔭 Watch-list |
| **ctrlX** | Bosch Rexroth | Ubuntu-core, app-store model (CODESYS runtime inside) | 🟡 Covered via CODESYS |
| **Virtual PLC** / **CODESYS Virtual Control** | Siemens / CODESYS | Containerized PLCs (Docker / K8s) | 🟡 / 🔭 |
## 5. Open-source runtimes (free — our test-bench substrates)
Used to **reconstruct and dynamically test** a customer device without touching
their network (provision-and-test).
| Runtime | Standard | Notes | Status |
| --- | --- | --- | --- |
| **OpenPLC** | IEC 61131-3 | Modbus-centric, education/small automation; uses MatIEC | 🧪 Test-bench (current) |
| **Beremiz + MatIEC** | IEC 61131-3 | Fuller open-source IDE; compiles ST/IL → C. Natural fidelity step-up from OpenPLC | 🧪 Test-bench (candidate) |
| **Eclipse 4diac (FORTE)** | IEC **61499** | Distributed, event-driven — a *different paradigm* from 61131-3's scan cycle | 🔭 Watch-list |
| **ProView** | — | Open-source process control + SCADA | 🔭 Watch-list |
## How we add support for a new runtime
- **Static (SAST / SBOM):** needs a parser for that runtime's **project format**
(and its library/package convention). This is the per-vendor work.
- **Dynamic (ICS probe / DAST):** already **vendor-agnostic** — it targets the
device's OT ports and WebVisu, not the runtime's file format. So a brand-new
ecosystem still gets dynamic coverage on day one.
::: tip Rule of thumb
Confirm whether a "non-CODESYS" controller is actually a **rebranded CODESYS**
runtime (Section 1) before assuming new work — most of the long tail is.
:::
-36
View File
@@ -1,36 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Demo PLCopen project — conveyor sorter. Deliberately vulnerable. -->
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types>
<pous>
<pou name="ConveyorCtrl" pouType="program">
<interface>
<localVars>
<variable name="AdminPwd">
<type><string/></type>
<initialValue><simpleValue value="password"/></initialValue>
</variable>
<variable name="Belt">
<type>
<array>
<dimension lower="0" upper="3"/>
<baseType><INT/></baseType>
</array>
</type>
</variable>
</localVars>
<inputVars>
<variable name="Slot"><type><INT/></type></variable>
</inputVars>
</interface>
<body>
<ST>
<xhtml xmlns="http://www.w3.org/1999/xhtml">Belt[Slot] := 1;
Ftp_Send(HOST := '192.168.1.5', PORT := 21, ENCRYPT := FALSE);
</xhtml>
</ST>
</body>
</pou>
</pous>
</types>
</project>
-56
View File
@@ -1,56 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Function Block Diagram (FBD) POU in PLCopen TC6 XML form. Demonstrates that
the scanner analyses graphical logic, not just Structured Text: the same
defects (cleartext Modbus master on 502, a hardcoded HMI password, a safety
enable driven FALSE) are here wired as blocks and in/out variables. -->
<project xmlns="http://www.plcopen.org/xml/tc6_0201">
<types>
<pous>
<pou name="PumpFbdCtrl" pouType="functionBlock">
<interface>
<inputVars>
<variable name="HmiPassword"><type><string/></type></variable>
<variable name="Safety_Enable"><type><BOOL/></type></variable>
<variable name="ServerIp"><type><string/></type></variable>
</inputVars>
</interface>
<body>
<FBD>
<!-- Modbus/TCP master: cleartext (AUTH := FALSE) on port 502 -->
<inVariable localId="1"><expression>'10.20.0.5'</expression><connectionPointOut/></inVariable>
<inVariable localId="2"><expression>502</expression><connectionPointOut/></inVariable>
<inVariable localId="3"><expression>FALSE</expression><connectionPointOut/></inVariable>
<block localId="10" typeName="Modbus_TCP_Master">
<inputVariables>
<variable formalParameter="IP">
<connectionPointIn><connection refLocalId="1"/></connectionPointIn>
</variable>
<variable formalParameter="PORT">
<connectionPointIn><connection refLocalId="2"/></connectionPointIn>
</variable>
<variable formalParameter="AUTH">
<connectionPointIn><connection refLocalId="3"/></connectionPointIn>
</variable>
</inputVariables>
<outputVariables/>
</block>
<!-- Hardcoded HMI password wired into an output -->
<inVariable localId="20"><expression>'admin123'</expression><connectionPointOut/></inVariable>
<outVariable localId="21">
<expression>HmiPassword</expression>
<connectionPointIn><connection refLocalId="20"/></connectionPointIn>
</outVariable>
<!-- Safety enable driven FALSE in logic -->
<inVariable localId="30"><expression>FALSE</expression><connectionPointOut/></inVariable>
<outVariable localId="31">
<expression>Safety_Enable</expression>
<connectionPointIn><connection refLocalId="30"/></connectionPointIn>
</outVariable>
</FBD>
</body>
</pou>
</pous>
</types>
</project>
-57
View File
@@ -1,57 +0,0 @@
(*
* Demo PLC program pump-station control (IEC 61131-3 Structured Text).
*
* Deliberately vulnerable, for the compliance-scanner PLC control-logic demo.
* Each issue below is flagged by pipeline::plc::rules.
*)
FUNCTION_BLOCK PumpStationCtrl
VAR_INPUT
OperatorCmd : INT; (* HMI command index untrusted *)
FlowSetpoint : REAL;
END_VAR
VAR_OUTPUT
PumpSpeed : REAL;
Fault : BOOL;
END_VAR
VAR
HmiPassword : STRING := 'admin123'; (* hardcoded + default credential *)
ApiKey : STRING := 'sk_live_9c1f2a'; (* hardcoded secret *)
PumpProfiles : ARRAY[0..7] OF REAL;
Safety_Enable : BOOL := TRUE;
Watchdog_Kick : INT := 1;
MeasuredFlow : REAL;
ScaleFactor : REAL;
i : INT;
END_VAR
(* Operator can index the profile table with an unvalidated command. *)
PumpSpeed := PumpProfiles[OperatorCmd];
(* Divisor is a live process value that can read zero on a stopped line. *)
ScaleFactor := FlowSetpoint / MeasuredFlow;
(* Safety interlock disabled straight from application logic. *)
IF OperatorCmd = 99 THEN
Safety_Enable := FALSE;
Watchdog_Kick := 0;
END_IF;
(* Unauthenticated Modbus/TCP link on the cleartext OT port. *)
Modbus_TCP_Connect(IP := '10.10.5.20', PORT := 502, AUTH := FALSE, PASSWORD := 'plc');
(* Unstructured jump around the fault handler. *)
IF MeasuredFlow > 1000.0 THEN
JMP trip;
END_IF;
(* A correctly guarded division must NOT be flagged. *)
IF ScaleFactor <> 0.0 THEN
PumpSpeed := PumpSpeed / ScaleFactor;
END_IF;
RETURN;
trip:
Fault := TRUE;
PumpSpeed := 0.0;
END_FUNCTION_BLOCK
-92
View File
@@ -1,92 +0,0 @@
(*
* Pedestrian-crossing traffic-light controller.
*
* Structure adapted from the classic OpenPLC "traffic light" example
* (github.com/thiagoralves/OpenPLC_v3 examples) a timed state machine
* driving vehicle + pedestrian lamps, extended with a SCADA/Modbus link
* and a maintenance override so it reads like a real deployed program.
*
* The control logic itself is sound; the security-relevant defects are the
* kind that slip into field code under deadline: a hardcoded SCADA password,
* a cleartext Modbus/TCP master, and a maintenance mode that drops the
* pedestrian safety permit. Everything else should stay quiet.
*)
PROGRAM TrafficLight
VAR
State : INT := 0; (* 0 GreenVeh, 1 Amber, 2 RedVeh/WalkPed, 3 FlashPed *)
Tmr : TON;
StateElapsed : TIME;
CycleMs : DINT := 0;
(* Lamp outputs *)
VehGreen : BOOL := FALSE;
VehAmber : BOOL := FALSE;
VehRed : BOOL := FALSE;
PedWalk : BOOL := FALSE;
PedStop : BOOL := TRUE;
(* Pedestrian safety permit must be TRUE before the WALK phase asserts *)
PedPermit : BOOL := TRUE;
PedButton : BOOL := FALSE;
(* SCADA / remote monitoring *)
ScadaUser : STRING := 'operator';
ScadaPassword : STRING := 'Tr@ffic2019'; (* hardcoded SCADA credential *)
ModbusReady : BOOL := FALSE;
(* Maintenance override *)
MaintMode : BOOL := FALSE;
LampCount : INT := 5;
DutyPct : INT;
END_VAR
(* ---- SCADA uplink: publish state to the control room over Modbus/TCP ---- *)
IF NOT ModbusReady THEN
Modbus_TCP_Master(IP := '10.20.0.5', PORT := 502, AUTH := FALSE, USER := ScadaUser, PASS := ScadaPassword);
ModbusReady := TRUE;
END_IF;
(* ---- Duty-cycle for the flashing pedestrian lamp (guarded division) ---- *)
IF LampCount <> 0 THEN
DutyPct := (CycleMs * 100) / LampCount;
END_IF;
(* ---- Maintenance override: flash amber, hand control to the technician ---- *)
IF MaintMode THEN
VehGreen := FALSE;
VehRed := FALSE;
VehAmber := NOT VehAmber;
PedPermit := FALSE; (* drops the pedestrian safety permit in code *)
PedWalk := FALSE;
PedStop := TRUE;
ELSE
(* ---- Normal timed state machine ---- *)
Tmr(IN := TRUE, PT := T#5s);
StateElapsed := Tmr.ET;
CASE State OF
0: (* vehicles go, pedestrians stop *)
VehGreen := TRUE; VehAmber := FALSE; VehRed := FALSE;
PedWalk := FALSE; PedStop := TRUE;
IF PedButton AND Tmr.Q THEN
State := 1; Tmr(IN := FALSE);
END_IF;
1: (* amber transition *)
VehGreen := FALSE; VehAmber := TRUE;
IF Tmr.Q THEN State := 2; Tmr(IN := FALSE); END_IF;
2: (* vehicles stop, pedestrians walk only if permitted *)
VehAmber := FALSE; VehRed := TRUE;
IF PedPermit THEN
PedWalk := TRUE; PedStop := FALSE;
END_IF;
IF Tmr.Q THEN State := 3; Tmr(IN := FALSE); END_IF;
3: (* flashing don't-walk before returning to green *)
PedWalk := NOT PedWalk;
IF Tmr.Q THEN
State := 0; PedButton := FALSE; Tmr(IN := FALSE);
END_IF;
ELSE
State := 0;
END_CASE;
END_IF;
END_PROGRAM