video-generation

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (/mnt/skills/public/video-generation/scripts/generate.py) to process video generation requests. This is the core functionality of the skill and uses standard argument parsing.
  • [EXTERNAL_DOWNLOADS]: The Python script communicates with Google's Generative Language API (generativelanguage.googleapis.com) to submit video generation tasks and download the resulting video files. These operations target a well-known service and are documented clearly in the script.
  • [DATA_EXFILTRATION]: While the script sends local files (prompt JSON and reference images) to an external API, it strictly targets the official Google Gemini API endpoints. It uses the GEMINI_API_KEY environment variable securely rather than hardcoding credentials.
  • [PROMPT_INJECTION]: The skill contains instructions to the agent to follow a specific workflow, but no attempts to override system safety guidelines or extract system prompts were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:27 AM
Security Audit — agent-trust-hub — video-generation