code-reviewer
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: 0.90). The skill explicitly checks out remote GitHub pull requests (via "gh pr checkout <PR_NUMBER>") and reads PR descriptions and comments from GitHub, which are untrusted, user-generated third-party contents that the agent ingests during its review workflow.
Audit Metadata