create-tool
Warn
Audited by Snyk on Feb 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill includes an HTML widget template (Template D) that returns markup loading external resources (e.g., and ), and the metadata examples enable widgetAccessible/resultCanProduceWidget behavior so external third‑party scripts could run and interact with the agent, creating an indirect prompt‑injection surface.
Audit Metadata