codeql
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs fetching and using public query packs and releases from GitHub (e.g., "codeql pack download trailofbits/..." and the GitHub releases URL) — untrusted third-party content that the CodeQL analysis workflow ingests and that can materially influence analysis results and downstream decisions.
Audit Metadata