caveman-review
Warn
Audited by Snyk on Apr 8, 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). Yes — SKILL.md explicitly says the assistant auto-triggers for and is invoked to "review this PR" / "review the diff", so it ingests user-generated pull request diffs (untrusted third-party content) which the agent must read and use to decide actions/comments.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata