3d-asset-generation

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions focus on domain-specific tasks for 3D production, such as mesh QA, cost discipline, and scene normalization in Blender. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting data (3D models) from external APIs like fal.ai and Atlas. However, it includes a 'Mandatory mesh QA' protocol that requires inspection of downloaded artifacts within a controlled environment (Blender) before approval, which serves as a procedural safeguard against malformed or malicious asset files.
  • [EXTERNAL_DOWNLOADS]: The skill references downloads from well-known 3D asset providers and catalogs. These references are used for their intended purpose in the asset generation workflow and do not involve the execution of untrusted scripts or binary payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM