feat: findings refinement, new scanners, and deployment tooling (#6)

compliance-agent/src/pipeline/gitleaks.rs

@@ -0,0 +1,130 @@
+use std::path::Path;
+
+use compliance_core::models::{Finding, ScanType, Severity};
+use compliance_core::traits::{ScanOutput, Scanner};
+use compliance_core::CoreError;
+
+use crate::pipeline::dedup;
+
+pub struct GitleaksScanner;
+
+impl Scanner for GitleaksScanner {
+    fn name(&self) -> &str {
+        "gitleaks"
+    }
+
+    fn scan_type(&self) -> ScanType {
+        ScanType::SecretDetection
+    }
+
+    async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
+        let output = tokio::process::Command::new("gitleaks")
+            .args([
+                "detect",
+                "--source",
+                ".",
+                "--report-format",
+                "json",
+                "--report-path",
+                "/dev/stdout",
+                "--no-banner",
+                "--exit-code",
+                "0",
+            ])
+            .current_dir(repo_path)
+            .output()
+            .await
+            .map_err(|e| CoreError::Scanner {
+                scanner: "gitleaks".to_string(),
+                source: Box::new(e),
+            })?;
+
+        if output.stdout.is_empty() {
+            return Ok(ScanOutput::default());
+        }
+
+        let results: Vec<GitleaksResult> =
+            serde_json::from_slice(&output.stdout).unwrap_or_default();
+
+        let findings = results
+            .into_iter()
+            .filter(|r| !is_allowlisted(&r.file))
+            .map(|r| {
+                let severity = match r.rule_id.as_str() {
+                    s if s.contains("private-key") => Severity::Critical,
+                    s if s.contains("token") || s.contains("password") || s.contains("secret") => {
+                        Severity::High
+                    }
+                    s if s.contains("api-key") => Severity::High,
+                    _ => Severity::Medium,
+                };
+
+                let fingerprint = dedup::compute_fingerprint(&[
+                    repo_id,
+                    &r.rule_id,
+                    &r.file,
+                    &r.start_line.to_string(),
+                ]);
+
+                let title = format!("Secret detected: {}", r.description);
+                let description = format!(
+                    "Potential secret ({}) found in {}:{}. Match: {}",
+                    r.rule_id,
+                    r.file,
+                    r.start_line,
+                    r.r#match.chars().take(80).collect::<String>(),
+                );
+
+                let mut finding = Finding::new(
+                    repo_id.to_string(),
+                    fingerprint,
+                    "gitleaks".to_string(),
+                    ScanType::SecretDetection,
+                    title,
+                    description,
+                    severity,
+                );
+                finding.rule_id = Some(r.rule_id);
+                finding.file_path = Some(r.file);
+                finding.line_number = Some(r.start_line);
+                finding.code_snippet = Some(r.r#match);
+                finding
+            })
+            .collect();
+
+        Ok(ScanOutput {
+            findings,
+            sbom_entries: Vec::new(),
+        })
+    }
+}
+
+/// Skip files that commonly contain example/placeholder secrets
+fn is_allowlisted(file_path: &str) -> bool {
+    let lower = file_path.to_lowercase();
+    lower.ends_with(".env.example")
+        || lower.ends_with(".env.sample")
+        || lower.ends_with(".env.template")
+        || lower.contains("/test/")
+        || lower.contains("/tests/")
+        || lower.contains("/fixtures/")
+        || lower.contains("/testdata/")
+        || lower.contains("mock")
+        || lower.ends_with("_test.go")
+        || lower.ends_with(".test.ts")
+        || lower.ends_with(".test.js")
+        || lower.ends_with(".spec.ts")
+        || lower.ends_with(".spec.js")
+}
+
+#[derive(serde::Deserialize)]
+#[serde(rename_all = "PascalCase")]
+struct GitleaksResult {
+    description: String,
+    #[serde(rename = "RuleID")]
+    rule_id: String,
+    file: String,
+    start_line: u32,
+    #[serde(rename = "Match")]
+    r#match: String,
+}