video-director

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and descriptors from the production manifest (e.g., brief.prompt, shot.still.prompt) and interpolates them into calls for other skills and models.
  • Ingestion points: Untrusted data enters the agent context through the manifest.json file, specifically the prompt and description fields.
  • Boundary markers: No explicit delimiters or instructions are provided to the downstream agents/models to ignore embedded instructions within these prompts.
  • Capability inventory: The skill has the capability to execute shell commands (ffmpeg, ffprobe) and invoke other Python scripts via subprocess.run in scripts/direct.py.
  • Sanitization: There is no explicit sanitization or validation of the prompt content before it is passed to the ComfyUI client or the VLM judge.
  • [COMMAND_EXECUTION]: The driver script scripts/direct.py uses subprocess.run() to execute various tasks.
  • Evidence: The sh method in scripts/direct.py executes commands such as ffmpeg, ffprobe, and various comfy_client.py or judge.py scripts located in sibling skill folders.
  • Context: While these calls use shlex.quote for logging and pass arguments as a list (reducing shell injection risk), they represent the primary mechanism through which the skill interacts with the host system.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 08:11 PM