pull-request-tool
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: 0.90). This skill explicitly fetches and acts on GitHub pull request data and user comments (see "FETCH PR" and "LIST COMMENTS" / usage examples referencing pr-number and repository), which are untrusted, user-generated third-party content that the agent reads and can use to decide actions like merging or replying.
Audit Metadata