skills-manager
Warn
Audited by Snyk on Feb 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). This skill fetches, clones, and installs arbitrary public GitHub repositories specified as owner/repo (via save/clone/add/install scripts), which are untrusted, user-generated third‑party contents that the agent will read and execute as part of its workflow.
Audit Metadata