implement
Fail
Audited by Snyk on Nov 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (medium risk: 0.30). The skill instructs the user or agent to install required skills via
npx skills@latest add toy-crane/skills --skill <name>, which downloads and executes code from an npm package and GitHub repository.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow invokes
babysit-pr, which monitors and interacts with GitHub pull requests, PR review bots, and CI comments containing outsider-authored free text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill references installation of
toy-crane/skillsfrom GitHub vianpx skills@latest add toy-crane/skills --skill <name>, which constitutes an unverifiable runtime external dependency from an unofficial third-party repository.
Issues (3)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata