create-scene

Warn

Audited by Snyk on Apr 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch external preview thumbnails and download 3D models from public URLs (e.g., "fetch the preview thumbnail (the preview: URL at the end of each catalog line)" and the curl example to https://models.dclregenesislabs.xyz/...), which are untrusted third‑party resources used to choose and import assets and thus can influence subsequent tooling and decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 05:20 PM
Issues
1
Security Audit — snyk — create-scene