gh-pr-codex-review-loop
Warn
Audited by Snyk on Apr 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 bundled script (scripts/pr-review-loop.mjs) explicitly queries GitHub via the GraphQL snapshot and thread-comments queries to fetch PR comments, review summaries, reactions, and reviewThreads (user-generated content from PR participants), which the skill parses and uses to decide actions like stopping the loop, classifying threads, and resolving threads; this exposes the agent to untrusted third-party content from GitHub PR comments that could carry indirect prompt-injection instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata