merge-pr
Warn
Audited by Snyk on Feb 15, 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 operates on GitHub pull requests (it asks for a PR number or URL and its run/verify steps extract PR metadata such as author email and comment_url and handle PR comments), so it ingests user-generated, public PR/comments from third-party sources.
Audit Metadata