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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:18 PM