find-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: 0.90). This skill instructs the agent to search and present/install skills from open/public sources (e.g., skills.sh and GitHub or "other sources") via the Skills CLI, meaning it fetches and interprets untrusted, user-generated third-party content as part of its workflow.
Audit Metadata