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
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:20 AM