feat: pentest onboarding — streaming, browser automation, reports, user cleanup (#16)

Complete pentest feature overhaul: SSE streaming, session-persistent browser tool (CDP), AES-256 credential encryption, auto-screenshots in reports, code-level remediation correlation, SAST triage chunking, context window optimization, test user cleanup (Keycloak/Auth0/Okta), wizard dropdowns, attack chain improvements, architecture docs with Mermaid diagrams.

Co-authored-by: Sharang Parnerkar <parnerkarsharang@gmail.com>
Reviewed-on: #16

compliance-agent/src/pentest/report/html/mod.rs

@@ -0,0 +1,518 @@
+mod appendix;
+mod attack_chain;
+mod cover;
+mod executive_summary;
+mod findings;
+mod scope;
+mod styles;
+
+use super::ReportContext;
+
+#[allow(clippy::format_in_format_args)]
+pub(super) fn build_html_report(ctx: &ReportContext) -> String {
+    let session = &ctx.session;
+    let session_id = session
+        .id
+        .map(|oid| oid.to_hex())
+        .unwrap_or_else(|| "-".to_string());
+    let date_str = session
+        .started_at
+        .format("%B %d, %Y at %H:%M UTC")
+        .to_string();
+    let date_short = session.started_at.format("%B %d, %Y").to_string();
+    let completed_str = session
+        .completed_at
+        .map(|d| d.format("%B %d, %Y at %H:%M UTC").to_string())
+        .unwrap_or_else(|| "In Progress".to_string());
+
+    // Collect unique tool names used
+    let tool_names: Vec<String> = {
+        let mut names: Vec<String> = ctx
+            .attack_chain
+            .iter()
+            .map(|n| n.tool_name.clone())
+            .collect();
+        names.sort();
+        names.dedup();
+        names
+    };
+
+    // Find the best app screenshot for the cover page:
+    // prefer the first navigate to the target URL that has a screenshot,
+    // falling back to any navigate with a screenshot
+    let app_screenshot: Option<String> = ctx
+        .attack_chain
+        .iter()
+        .filter(|n| n.tool_name == "browser")
+        .filter_map(|n| {
+            n.tool_output
+                .as_ref()?
+                .get("screenshot_base64")?
+                .as_str()
+                .filter(|s| !s.is_empty())
+                .map(|s| s.to_string())
+        })
+        // Skip the Keycloak login page screenshots — prefer one that shows the actual app
+        .find(|_| {
+            ctx.attack_chain
+                .iter()
+                .filter(|n| n.tool_name == "browser")
+                .any(|n| {
+                    n.tool_output
+                        .as_ref()
+                        .and_then(|o| o.get("title"))
+                        .and_then(|t| t.as_str())
+                        .is_some_and(|t| t.contains("Compliance") || t.contains("Dashboard"))
+                })
+        })
+        .or_else(|| {
+            // Fallback: any screenshot
+            ctx.attack_chain
+                .iter()
+                .filter(|n| n.tool_name == "browser")
+                .filter_map(|n| {
+                    n.tool_output
+                        .as_ref()?
+                        .get("screenshot_base64")?
+                        .as_str()
+                        .filter(|s| !s.is_empty())
+                        .map(|s| s.to_string())
+                })
+                .next()
+        });
+
+    let styles_html = styles::styles();
+    let cover_html = cover::cover(
+        &ctx.target_name,
+        &session_id,
+        &date_short,
+        &ctx.target_url,
+        &ctx.requester_name,
+        &ctx.requester_email,
+        app_screenshot.as_deref(),
+    );
+    let exec_html = executive_summary::executive_summary(
+        &ctx.findings,
+        &ctx.target_name,
+        &ctx.target_url,
+        tool_names.len(),
+        session.tool_invocations,
+        session.success_rate(),
+    );
+    let scope_html = scope::scope(
+        session,
+        &ctx.target_name,
+        &ctx.target_url,
+        &date_str,
+        &completed_str,
+        &tool_names,
+        ctx.config.as_ref(),
+    );
+    let findings_html = findings::findings(
+        &ctx.findings,
+        &ctx.sast_findings,
+        &ctx.code_context,
+        &ctx.sbom_entries,
+    );
+    let chain_html = attack_chain::attack_chain(&ctx.attack_chain);
+    let appendix_html = appendix::appendix(&session_id);
+
+    format!(
+        r#"<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Penetration Test Report — {target_name}</title>
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+<link href="https://fonts.googleapis.com/css2?family=Libre+Baskerville:ital,wght@0,400;0,700;1,400&family=Source+Sans+3:ital,wght@0,300;0,400;0,600;0,700&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
+{styles_html}
+</head>
+<body>
+
+{cover_html}
+
+{exec_html}
+
+{scope_html}
+
+{findings_html}
+
+{chain_html}
+
+{appendix_html}
+"#,
+        target_name = html_escape(&ctx.target_name),
+    )
+}
+
+fn tool_category(tool_name: &str) -> &'static str {
+    let name = tool_name.to_lowercase();
+    if name.contains("nmap") || name.contains("port") {
+        return "Network Reconnaissance";
+    }
+    if name.contains("nikto") || name.contains("header") {
+        return "Web Server Analysis";
+    }
+    if name.contains("zap") || name.contains("spider") || name.contains("crawl") {
+        return "Web Application Scanning";
+    }
+    if name.contains("sqlmap") || name.contains("sqli") || name.contains("sql") {
+        return "SQL Injection Testing";
+    }
+    if name.contains("xss") || name.contains("cross-site") {
+        return "Cross-Site Scripting Testing";
+    }
+    if name.contains("dir")
+        || name.contains("brute")
+        || name.contains("fuzz")
+        || name.contains("gobuster")
+    {
+        return "Directory Enumeration";
+    }
+    if name.contains("ssl") || name.contains("tls") || name.contains("cert") {
+        return "SSL/TLS Analysis";
+    }
+    if name.contains("api") || name.contains("endpoint") {
+        return "API Security Testing";
+    }
+    if name.contains("auth") || name.contains("login") || name.contains("credential") {
+        return "Authentication Testing";
+    }
+    if name.contains("cors") {
+        return "CORS Testing";
+    }
+    if name.contains("csrf") {
+        return "CSRF Testing";
+    }
+    if name.contains("nuclei") || name.contains("template") {
+        return "Vulnerability Scanning";
+    }
+    if name.contains("whatweb") || name.contains("tech") || name.contains("wappalyzer") {
+        return "Technology Fingerprinting";
+    }
+    "Security Testing"
+}
+
+fn html_escape(s: &str) -> String {
+    s.replace('&', "&amp;")
+        .replace('<', "&lt;")
+        .replace('>', "&gt;")
+        .replace('"', "&quot;")
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::dast::{DastFinding, DastVulnType};
+    use compliance_core::models::finding::Severity;
+    use compliance_core::models::pentest::{
+        AttackChainNode, AttackNodeStatus, PentestSession, PentestStrategy,
+    };
+
+    // ── html_escape ──────────────────────────────────────────────────
+
+    #[test]
+    fn html_escape_handles_ampersand() {
+        assert_eq!(html_escape("a & b"), "a &amp; b");
+    }
+
+    #[test]
+    fn html_escape_handles_angle_brackets() {
+        assert_eq!(html_escape("<script>"), "&lt;script&gt;");
+    }
+
+    #[test]
+    fn html_escape_handles_quotes() {
+        assert_eq!(html_escape(r#"key="val""#), "key=&quot;val&quot;");
+    }
+
+    #[test]
+    fn html_escape_handles_all_special_chars() {
+        assert_eq!(
+            html_escape(r#"<a href="x">&y</a>"#),
+            "&lt;a href=&quot;x&quot;&gt;&amp;y&lt;/a&gt;"
+        );
+    }
+
+    #[test]
+    fn html_escape_no_change_for_plain_text() {
+        assert_eq!(html_escape("hello world"), "hello world");
+    }
+
+    #[test]
+    fn html_escape_empty_string() {
+        assert_eq!(html_escape(""), "");
+    }
+
+    // ── tool_category ────────────────────────────────────────────────
+
+    #[test]
+    fn tool_category_nmap() {
+        assert_eq!(tool_category("nmap_scan"), "Network Reconnaissance");
+    }
+
+    #[test]
+    fn tool_category_port_scanner() {
+        assert_eq!(tool_category("port_scanner"), "Network Reconnaissance");
+    }
+
+    #[test]
+    fn tool_category_nikto() {
+        assert_eq!(tool_category("nikto"), "Web Server Analysis");
+    }
+
+    #[test]
+    fn tool_category_header_check() {
+        assert_eq!(
+            tool_category("security_header_check"),
+            "Web Server Analysis"
+        );
+    }
+
+    #[test]
+    fn tool_category_zap_spider() {
+        assert_eq!(tool_category("zap_spider"), "Web Application Scanning");
+    }
+
+    #[test]
+    fn tool_category_sqlmap() {
+        assert_eq!(tool_category("sqlmap"), "SQL Injection Testing");
+    }
+
+    #[test]
+    fn tool_category_xss_scanner() {
+        assert_eq!(tool_category("xss_scanner"), "Cross-Site Scripting Testing");
+    }
+
+    #[test]
+    fn tool_category_dir_bruteforce() {
+        assert_eq!(tool_category("dir_bruteforce"), "Directory Enumeration");
+    }
+
+    #[test]
+    fn tool_category_gobuster() {
+        assert_eq!(tool_category("gobuster"), "Directory Enumeration");
+    }
+
+    #[test]
+    fn tool_category_ssl_check() {
+        assert_eq!(tool_category("ssl_check"), "SSL/TLS Analysis");
+    }
+
+    #[test]
+    fn tool_category_tls_scan() {
+        assert_eq!(tool_category("tls_scan"), "SSL/TLS Analysis");
+    }
+
+    #[test]
+    fn tool_category_api_test() {
+        assert_eq!(tool_category("api_endpoint_test"), "API Security Testing");
+    }
+
+    #[test]
+    fn tool_category_auth_bypass() {
+        assert_eq!(tool_category("auth_bypass_check"), "Authentication Testing");
+    }
+
+    #[test]
+    fn tool_category_cors() {
+        assert_eq!(tool_category("cors_check"), "CORS Testing");
+    }
+
+    #[test]
+    fn tool_category_csrf() {
+        assert_eq!(tool_category("csrf_scanner"), "CSRF Testing");
+    }
+
+    #[test]
+    fn tool_category_nuclei() {
+        assert_eq!(tool_category("nuclei"), "Vulnerability Scanning");
+    }
+
+    #[test]
+    fn tool_category_whatweb() {
+        assert_eq!(tool_category("whatweb"), "Technology Fingerprinting");
+    }
+
+    #[test]
+    fn tool_category_unknown_defaults_to_security_testing() {
+        assert_eq!(tool_category("custom_tool"), "Security Testing");
+    }
+
+    #[test]
+    fn tool_category_is_case_insensitive() {
+        assert_eq!(tool_category("NMAP_Scanner"), "Network Reconnaissance");
+        assert_eq!(tool_category("SQLMap"), "SQL Injection Testing");
+    }
+
+    // ── build_html_report ────────────────────────────────────────────
+
+    fn make_session(strategy: PentestStrategy) -> PentestSession {
+        let mut s = PentestSession::new("target-1".into(), strategy);
+        s.tool_invocations = 5;
+        s.tool_successes = 4;
+        s.findings_count = 2;
+        s.exploitable_count = 1;
+        s
+    }
+
+    fn make_finding(severity: Severity, title: &str, exploitable: bool) -> DastFinding {
+        let mut f = DastFinding::new(
+            "run-1".into(),
+            "target-1".into(),
+            DastVulnType::Xss,
+            title.into(),
+            "description".into(),
+            severity,
+            "https://example.com/test".into(),
+            "GET".into(),
+        );
+        f.exploitable = exploitable;
+        f
+    }
+
+    fn make_attack_node(tool_name: &str) -> AttackChainNode {
+        let mut node = AttackChainNode::new(
+            "session-1".into(),
+            "node-1".into(),
+            tool_name.into(),
+            serde_json::json!({}),
+            "Testing this tool".into(),
+        );
+        node.status = AttackNodeStatus::Completed;
+        node
+    }
+
+    fn make_report_context(
+        findings: Vec<DastFinding>,
+        chain: Vec<AttackChainNode>,
+    ) -> ReportContext {
+        ReportContext {
+            session: make_session(PentestStrategy::Comprehensive),
+            target_name: "Test App".into(),
+            target_url: "https://example.com".into(),
+            findings,
+            attack_chain: chain,
+            requester_name: "Alice".into(),
+            requester_email: "alice@example.com".into(),
+            config: None,
+            sast_findings: Vec::new(),
+            sbom_entries: Vec::new(),
+            code_context: Vec::new(),
+        }
+    }
+
+    #[test]
+    fn report_contains_target_info() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("Test App"));
+        assert!(html.contains("https://example.com"));
+    }
+
+    #[test]
+    fn report_contains_requester_info() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("Alice"));
+        assert!(html.contains("alice@example.com"));
+    }
+
+    #[test]
+    fn report_shows_informational_risk_when_no_findings() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("INFORMATIONAL"));
+    }
+
+    #[test]
+    fn report_shows_critical_risk_with_critical_finding() {
+        let findings = vec![make_finding(Severity::Critical, "Critical XSS", true)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("CRITICAL"));
+    }
+
+    #[test]
+    fn report_shows_high_risk_without_critical() {
+        let findings = vec![make_finding(Severity::High, "High SQLi", false)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        // Should show HIGH, not CRITICAL
+        assert!(html.contains("HIGH"));
+    }
+
+    #[test]
+    fn report_shows_medium_risk_level() {
+        let findings = vec![make_finding(Severity::Medium, "Medium Issue", false)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("MEDIUM"));
+    }
+
+    #[test]
+    fn report_includes_finding_title() {
+        let findings = vec![make_finding(
+            Severity::High,
+            "Reflected XSS in /search",
+            true,
+        )];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("Reflected XSS in /search"));
+    }
+
+    #[test]
+    fn report_shows_exploitable_badge() {
+        let findings = vec![make_finding(Severity::Critical, "SQLi", true)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        // The report should mark exploitable findings
+        assert!(html.contains("EXPLOITABLE"));
+    }
+
+    #[test]
+    fn report_includes_attack_chain_tool_names() {
+        let chain = vec![make_attack_node("nmap_scan"), make_attack_node("sqlmap")];
+        let ctx = make_report_context(vec![], chain);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("nmap_scan"));
+        assert!(html.contains("sqlmap"));
+    }
+
+    #[test]
+    fn report_is_valid_html_structure() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("<!DOCTYPE html>") || html.contains("<html"));
+        assert!(html.contains("</html>"));
+    }
+
+    #[test]
+    fn report_strategy_appears() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        // PentestStrategy::Comprehensive => "comprehensive"
+        assert!(html.contains("comprehensive") || html.contains("Comprehensive"));
+    }
+
+    #[test]
+    fn report_finding_count_is_correct() {
+        let findings = vec![
+            make_finding(Severity::Critical, "F1", true),
+            make_finding(Severity::High, "F2", false),
+            make_finding(Severity::Low, "F3", false),
+        ];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        // The total count "3" should appear somewhere
+        assert!(
+            html.contains(">3<")
+                || html.contains(">3 ")
+                || html.contains("3 findings")
+                || html.contains("3 Total")
+        );
+    }
+}