blender-asset-validation

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The test script scripts/test_evidence_blender.py invokes subprocess.run to launch Blender in background mode for smoke testing. This execution is restricted to verifying internal scripts using local temporary directories and predefined fixtures, representing standard development practice.- [INDIRECT_PROMPT_INJECTION]: The skill validates external assets such as .blend and .glb files. It addresses potential indirect injection risks by employing dedicated Python scripts to convert binary mesh data into structured JSON metrics and multiview renders, effectively isolating the agent from untrusted raw content within the source files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 08:31 AM