find-skills
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill instructs the agent to search and fetch skills from public third-party sources (via
npx skills find [query], links to https://skills.sh/ and GitHub owner/repo pages) and to present and optionally install those community-authored packages, which are untrusted user-generated content that can influence actions like installing and running code.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). This skill explicitly instructs running npx skills add to fetch and install skills at runtime (e.g., vercel-labs/agent-skills@vercel-react-best-practices and https://skills.sh/), which will download and execute remote code from Git/GitHub and is a required runtime action to install those skills.
Audit Metadata