create-video-fal

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Python scripts to coordinate video generation through external media proxies.
  • [EXTERNAL_DOWNLOADS]: Downloads generated video assets from the FAL AI content delivery network via the GooseWorks proxy.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided JSON payloads containing prompts for generative video models. * Ingestion points: The --payload argument in gen_video.py accepts JSON input containing natural language prompts. * Boundary markers: Inputs are encapsulated and parsed as structured JSON objects. * Capability inventory: The skill is capable of performing network POST requests and writing downloaded files to local storage. * Sanitization: The skill validates JSON syntax but does not filter the content of the prompt passed to the generative model.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 01:55 PM