blender-director
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill is centered around generating and executing a Python script ('build.py') to automate Blender operations. This involves runtime generation of executable code that controls the 3D environment via the Blender command-line interface.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted external data to generate animation logic.
- Ingestion points: Sitcom dialogue scripts (Step 1), speech transcriptions (Step 2), and timing data from 'timeline.json' (Step 3).
- Boundary markers: The instructions do not prescribe the use of specific delimiters or 'ignore' instructions to isolate user-provided dialogue from the agent's logic.
- Capability inventory: The resulting scripts use the 'bpy' (Blender Python) API, which possesses the capability to perform file operations and execute system commands.
- Sanitization: There are no requirements for validating or escaping the input text before it is used as parameters within the generated Python build scripts.
Audit Metadata