skill
Warn
Audited by Snyk on May 12, 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). The SKILL.md explicitly instructs fetching and installing skills from the public "belt registry" (e.g., "belt skill use <namespace/name>" and "belt skill install <namespace/name>"), which are user-published third‑party skill definitions the agent will read/ingest and could change its behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata