review-reply
Warn
Audited by Snyk on Mar 31, 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.md explicitly fetches and ingests user-generated PR and issue comments from GitHub (e.g., "gh api repos/{owner}/{repo}/pulls/{number}/comments", reviews, and "repos/{owner}/{repo}/issues/{number}/comments" and GraphQL reviewThreads), which the agent must read and act on (decide fixes, post replies, resolve threads), exposing it to untrusted third‑party content that could carry indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata