install-skills
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and lists skills from public GitHub repositories and arbitrary URLs (e.g., "npx ... skills add owner/repo", full GitHub URLs, or direct repo paths), so the agent will ingest and act on untrusted third‑party code/content that could contain indirect prompt injection.
Audit Metadata