homebrew-cask-authoring
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to fetch and verify arbitrary public download URLs and to search/read GitHub PRs and other web pages (e.g., "check open PRs", "verify the download URL works in browser", linked GitHub/search URLs), i.e., ingesting untrusted user-generated third‑party content that can change cask decisions and follow-up actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata