video-generator
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user input and transmits it to external AI services, exposing a surface for potential prompt injection. 1. Ingestion points: Prompt argument in scripts/generate_video.py. 2. Boundary markers: Absent. 3. Capability inventory: Network requests to Google and OpenAI, and file system writes in scripts/generate_video.py. 4. Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill requires the execution of a Python script to perform its primary function, involving network access and local file creation.
- [EXTERNAL_DOWNLOADS]: The skill downloads generated video media from official Google and OpenAI endpoints.
Audit Metadata