engineer-review
Warn
Audited by Snyk on Feb 24, 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 skill explicitly fetches PR diffs from GitHub (Step 1: "If a PR number is provided:
gh pr diff [number]" in SKILL.md), meaning it ingests untrusted user-generated third-party content (public PRs/diffs) that the agent reads and uses to drive reviewer decisions and next actions—creating a clear avenue for indirect prompt injection.
Audit Metadata