review
Warn
Audited by Snyk on Apr 7, 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.md explicitly supports "--pr N for PR mode (GitHub review comments)", which indicates the agent will ingest user-generated GitHub PR content/comments as part of its review workflow, exposing it to untrusted third-party input that could carry indirect prompt-injection instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata