add-3d-models
Warn
Audited by Snyk on Apr 13, 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 explicitly instructs the agent to fetch and download models and previews from the OpenDCL model catalog (e.g., example curl commands and preview: https://models.dclregenesislabs.xyz/... in the "Free 3D Models — OpenDCL Catalog" section) and to parse model metadata (animations, mesh/node names, bounding boxes) which the agent uses to decide Animator components, collision masks, placement, and other actions—i.e., untrusted third‑party content is fetched and directly influences tool use and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata