jmb-review-pr
Fail
Audited by Snyk on Nov 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's stated purpose is a read-only PR review that posts a report, and nothing in it turns the agent against the user; the one sketchy point is that pending-review.sh's comment says the kit's hook judges the Bash call line and not what the script runs, which describes a gap in oversight without any sign of malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow reads GitHub PR text (title, body, and commit messages via
gh pr view) and ticket comments (viagh issue view <t> --comments), which outsiders can author on public or externally-filed issues and PRs, and it does so without the agent selecting a specific outsider item.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata