code-review
Warn
Audited by Snyk on Feb 25, 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). This skill's mandatory workflow explicitly fetches and reads GitHub PR content (via commands like "gh pr view" and "gh pr diff") and the PR descriptions/diffs/changed files are untrusted, user-generated third‑party content that the agent must interpret and use to decide actions (post comments, request changes), creating an avenue for indirect prompt injection.
Audit Metadata