resolve-pr-threads
Warn
Audited by Snyk on Mar 2, 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's SKILL.md "Collect (single snapshot)" step explicitly fetches review threads, inline comments, and sub-comments from the current PR (user-generated, third-party content) and requires the agent to read and act on them (replies, commits, tagging), so untrusted content can directly influence actions.
Audit Metadata