scene-readiness

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely descriptive and instruction-based. It does not contain scripts (Python, JavaScript, etc.) or executable binaries.
  • [COMMAND_EXECUTION]: The skill documentation explicitly states an 'Official runtime boundary' which forbids the execution or emission of Python code and prohibits running Blender.
  • [REMOTE_CODE_EXECUTION]: All external references are to official documentation (Blender.org) or trusted tutorial platforms (Claude.com). There are no patterns of downloading and executing remote scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for reports from other tools (e.g., polycount-budget-checker). However, it includes strict boundary markers and a 'downgrade-only' truth state policy that prevents external data from escalating the agent's perceived success or capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 01:08 AM