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
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 06:39 AM