turntable

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts within the Blender environment to manipulate 3D scenes and runs ffmpeg commands via the shell to encode video sequences.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because user-provided parameters are interpolated directly into executable Python and shell code blocks.
  • Ingestion points: Variable placeholders such as <OBJECT_NAME>, <OUTPUT>, and numeric parameters like duration and fps in SKILL.md.
  • Boundary markers: None. The skill does not use delimiters or instructions to the agent to treat these inputs strictly as data.
  • Capability inventory: The skill uses the os module for directory management, the bpy API for Blender automation, and shell access for ffmpeg processing.
  • Sanitization: There is no evidence of validation or escaping for the parameters before they are inserted into scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 11:50 PM
Security Audit — agent-trust-hub — turntable