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/skills from GitHub via npx skills@latest add toy-crane/skills --skill <name>, which constitutes an unverifiable runtime external dependency from an unofficial third-party repository.

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 08:40 AM
Issues
3