gh-fix-pr
Warn
Audited by Snyk on May 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill's script (scripts/inspect_pr_checks.py) and SKILL.md explicitly fetch and parse untrusted, user-generated GitHub content — e.g., PR reviews, inline review comments, issue comments, GraphQL review threads and CI logs via
gh api/GraphQL — and uses those comment bodies and log snippets to decide fixes, create plans, and automatically reply/resolve threads, so third-party content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata