skills/openaec-foundation/blender-bonsai-ifcopenshell-sverchok-claude-skill-package/blender-agents-code-validator/Gen Agent Trust Hub
blender-agents-code-validator
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and systematically analyze untrusted Blender Python code provided by users, which creates an indirect prompt injection surface.
- Ingestion points: User-provided scripts and addon source files (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data being analyzed.
- Capability inventory: The skill is capable of reading files and performing automated code modifications via 'Auto-Fix Patterns' defined in SKILL.md.
- Sanitization: No content sanitization or validation is performed on the analyzed code before it enters the agent's context.
Audit Metadata