find-skill
Warn
Audited by Snyk on May 4, 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). The SKILL.md explicitly instructs the agent to web_search/web_fetch public marketplaces and GitHub (e.g., skillsmp.com, claudemarketplaces.com, skillhub.club, and community GitHub repos) and to read each candidate's SKILL.md/description — all open, user-generated third‑party content that the agent will ingest and use to decide which skills to surface, so it could carry indirect prompt-injection content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata