code-review
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill directly ingests and interprets user-generated GitHub pull request content (via commands like "gh pr view --json ...", "gh pr view --comments", and "gh pr diff "), so it consumes untrusted third-party PR titles/bodies/commits/comments/diffs as part of its workflow and could be exposed to indirect prompt injection.
Audit Metadata