review-strategy
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and reviews user-provided files and Pull Request content (see triggers: "User asks to review a file or set of files" and "User asks to review a Pull Request"), which are untrusted, user-generated inputs the agent will read and interpret and therefore could contain indirect prompt-injection content.
Audit Metadata