blender-compositing-nodes

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill facilitates the generation and execution of Python scripts within the Blender environment using the bpy library. This functionality is mediated by the execute_blender_code tool. The execution is limited to the scope of a Blender session and follows standard industry practices for compositing automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it instructs the agent to generate Python code incorporating user-provided data, such as file paths for images and movie clips.
  • Ingestion points: User-provided parameters for compositor setups, including file paths and node settings defined in SKILL.md and references/python_api.md.
  • Boundary markers: None identified in the instructional content.
  • Capability inventory: Uses the execute_blender_code tool to run generated scripts which can perform file operations and scene mutations within Blender.
  • Sanitization: No explicit sanitization or validation logic is provided for user-supplied strings before they are interpolated into the generated Python templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:58 AM