whitebox-previs-executor

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local binaries including Blender, FFmpeg, and FFprobe to perform 3D rendering and video encoding. These operations use the subprocess module with argument lists, which avoids shell-based command injection vulnerabilities. The skill also implements isolation by redirecting environment variables like TEMP and LOCALAPPDATA to a local runtime directory.
  • Evidence: scripts/run_blender_previs.py, scripts/run_blender_rigged_fight.py, and scripts/render_previs.py contain logic for discovering and invoking these external tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes natural language video prompts from the user to generate 3D scene specifications. While this creates a potential surface for indirect injection, the skill employs strict schema validation and does not use the processed content in a way that would trigger further agent actions or privilege escalation.
  • Ingestion points: Natural language video descriptions provided by the user to the agent.
  • Boundary markers: Skill instructions direct the agent to transform input into the structured previs-compiler/1.0 JSON schema, acting as a structural boundary.
  • Capability inventory: Ability to write media files (MP4, .blend) and execute rendering software via subprocesses.
  • Sanitization: Generated JSON data is comprehensively validated by scripts/validate_compiled_previs.py and scripts/validate_spec.py before any rendering or execution occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 02:32 PM