fan-cam

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied event details and reaction descriptions to interpolate them into prompts for media generation models. It uses detailed templates and instructions to ensure the agent acts as a controller, maintaining the identity of the user and the realism of the broadcast context.
  • [COMMAND_EXECUTION]: Utilizes the genmedia CLI and standard shell utilities like jq to manage file uploads, verify model availability, and execute media generation pipelines. These actions are restricted to the primary functionality of the skill.
  • [EXTERNAL_DOWNLOADS]: Interacts with established AI services (OpenAI and Fal.ai) to process images and generate video content. The skill follows best practices by verifying endpoint schemas and pricing before execution and downloading final assets to specific local paths for user delivery.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:40 PM