zr-validate
Fail
Audited by Snyk on Nov 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a peer-review validation workflow with no obfuscation, credential theft, or covert triggers, but its merge-ready section tells the agent to merge the linked PR or "otherwise finalize the task," which contradicts its own statement that final merge execution is out of scope and could act on the user's repo in unexpected ways.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow runs
gh pr view ... --json reviews,commentsand reads the review summary and PR comments, which outside users can post to without the agent selecting a specific item, so this is GitHub PR reading and falls under medium.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata