video-generation

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local Python script (generate.py) to handle video generation requests. This is a standard practice for offloading complex API interactions from the core agent instructions.
  • [EXTERNAL_DOWNLOADS]: The Python script makes network requests to generativelanguage.googleapis.com to interact with the Gemini API. This is a trusted and well-known service endpoint for Google's AI services.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: While the script reads files (prompts and reference images) and transmits them to an external API, the destination is a legitimate Google service, and the operations are consistent with the skill's primary purpose of video generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 10:12 AM
Security Audit — agent-trust-hub — video-generation