skills/drawcall-ai/skills/gaia-assets/Gen Agent Trust Hub

gaia-assets

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data access were detected. The skill's functionality aligns with its stated purpose of managing game assets.
  • [EXTERNAL_DOWNLOADS]: The skill references the @drawcall/acta library, which is a vendor-owned resource for character state machines. It also utilizes the well-known three library for 3D rendering and environment effects.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The askFile tool is used to analyze external files such as GLB models and PNG images to answer questions about their content or style.
  • Boundary markers: The skill does not provide specific delimiters or instructions to ignore potential commands embedded within asset metadata.
  • Capability inventory: The agent possesses tools for creating and editing various game assets (createModel, createCharacter, editMap, etc.).
  • Sanitization: There are no explicit content validation or sanitization steps described for processing the asset files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 03:31 PM
Security Audit — agent-trust-hub — gaia-assets