anvil-level-design-blender

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to download the addon as a ZIP file from an external GitHub repository (https://github.com/alexjhetherington/anvil-level-design) and install it manually within Blender. This represents a reference to third-party code required for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processes for importing external texture images and hotspot configuration data via JSON files. This ingestion of untrusted external content represents a potential indirect prompt injection surface.
  • Ingestion points: Texture files loaded via the file browser for material application and hotspot mapping data exported/imported via JSON files.
  • Boundary markers: None explicitly mentioned in the documentation for sanitizing or isolating external data.
  • Capability inventory: The skill utilizes the Blender Python API (bpy) to perform mesh operations, material management, and UV mapping updates based on external inputs.
  • Sanitization: No specific validation or sanitization routines for the external JSON structure or image metadata are described in the code snippets provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 04:27 PM
Security Audit — agent-trust-hub — anvil-level-design-blender