find-skills
Warn
Audited by Snyk on Mar 5, 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's SKILL.md instructs the agent to call the public ClaWHub API (e.g., POST https://api.clawhub.com/v1/skills/search) to fetch community skill listings and then use returned skill IDs to chain executions, meaning untrusted, user-contributed skill data from the open hub is ingested and can directly influence subsequent tool use.
Audit Metadata