code-review
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly reads external pull request diffs and repository content (e.g., "gh pr diff ", "git diff", "git show") which can ingest untrusted, user-generated code/PR text from third-party GitHub repos that the agent is expected to interpret and use to drive review decisions.
Audit Metadata