Added Cap::DATA_EXFIL and taint fp and fn fixes on real repos (#59)

* feat: Enhance data exfiltration detection with source sensitivity gating for cookies and headers

* feat: Implement cross-file data exfiltration detection with parameter-specific gate filters

* feat: Add calibration tests and refine DATA_EXFIL severity scoring logic

* feat: Introduce per-detector configuration for data exfiltration suppression

* feat: Enhance DATA_EXFIL findings with destination field tracking in diagnostics and SARIF output

* feat: Add tainted body and URL handling for data exfiltration detection

* feat: Add integration tests and fixtures for DATA_EXFIL and SSRF detection in Go

* feat: Add Java integration tests and fixtures for DATA_EXFIL detection across multiple HTTP clients

* feat: Add synthetic externals handling for closure-captured variables in SSA

* feat: Implement closure-based suppression for resource leak findings

* feat: Add regression guards for shell-injection and taint propagation in for-of destructure patterns

* feat: Implement constructor cap narrowing for data exfiltration detection in HTTP request builders

* feat: Add gated sinks for data exfiltration detection in C and C++ using curl_easy_setopt

* feat: Implement DATA_EXFIL cap parity for backwards analysis and add integration tests

* feat: Add data exfiltration sinks for various languages and enhance documentation

* refactor: Simplify formatting and improve readability in various files

* refactor: Improve readability by simplifying conditional statements and adding clippy linting

* docs: Update CHANGELOG and comments for data exfiltration features and configuration

* docs: Clarify configuration instructions for data exfiltration trusted destinations

* docs: Enhance comments for evidence routing logic in data exfiltration
This commit is contained in:
Eli Peter 2026-05-01 10:59:52 -04:00 committed by GitHub
parent a438886217
commit 58f1794a4e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
189 changed files with 8421 additions and 383 deletions

View file

@ -594,6 +594,9 @@ function sinkCapKey(finding: FindingView): string | null {
const snippet = (finding.evidence?.sink?.snippet || '').toLowerCase();
const rule = finding.rule_id.toLowerCase();
if (rule.includes('data-exfiltration') || rule.includes('exfil'))
return 'data-exfil';
if (
/innerhtml|outerhtml|document\.write|dangerouslysetinnerhtml/.test(snippet)
)
@ -615,7 +618,6 @@ function sinkCapKey(finding: FindingView): string | null {
if (/readfile|fs\.|open\s*\(|path\.join/.test(snippet)) return 'path';
if (/\bfetch\b|\baxios\b|http\.|request\.|urlopen|curl/.test(snippet))
return 'ssrf';
if (rule.includes('xss')) return 'xss';
if (rule.includes('sql')) return 'sql';
if (rule.includes('cmd') || rule.includes('command')) return 'cmd-inject';
@ -663,6 +665,11 @@ const TAINT_REMEDIATION: Record<string, string[]> = {
'Replace dynamic code generation with a parser over an allowlisted grammar.',
'If scripting is required, sandbox it (VM / Web Worker with no DOM, seccomp).',
],
'data-exfil': [
'Do not put cookies, session tokens, or env secrets into outbound request bodies.',
'If the forward is intentional, allowlist the destination under `detectors.data_exfil.trusted_destinations` or route through a named wrapper the engine treats as a data-exfil sanitizer.',
'Use dedicated server-to-server credentials for the upstream call instead of forwarding the user session.',
],
};
const DEFAULT_TAINT_REMEDIATION: string[] = [