gbro-collage-broll
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions and scripts facilitate the installation of the google-genai and httpx Python packages. These are legitimate libraries from a well-known service provider used for the skill's primary functionality of interacting with the Gemini API.\n- [COMMAND_EXECUTION]: The skill executes local shell scripts and Python subprocesses to perform media processing tasks using ffmpeg and ffprobe. These actions are necessary for video editing, such as stripping audio and generating contact sheets, and are restricted to the skill's intended operational scope.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text to generate visual metaphors and video content. To mitigate potential injection risks where untrusted input might influence the agent's logic, the skill enforces a mandatory 'Three-Gate' approval process, requiring human verification of metaphors and still images before any high-cost video generation or complex API calls occur.
Audit Metadata