pr-review-handler
Warn
Audited by Snyk on Feb 21, 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 reads PR reviews and line-comments from GitHub (see SKILL.md "Fetch PR Information" gh commands and the examples in references/examples.md), which are untrusted, user-generated third-party content that the agent is instructed to interpret and act upon (e.g., change code, run tools, and post replies), creating a clear avenue for indirect prompt injection.
Audit Metadata