muapi-product-video-ad-maker
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the 'muapi' CLI and the service's official API endpoint ('api.muapi.ai') to perform image and video generation tasks. This behavior is entirely consistent with the skill's stated purpose and matches the vendor's infrastructure.- [COMMAND_EXECUTION]: The skill instructs the agent to execute 'muapi' CLI commands for authentication and task processing. This is a legitimate use of specialized tooling required for the skill's primary functionality.- [EXTERNAL_DOWNLOADS]: The skill references 'api.muapi.ai' for API-based model inference. As this is the official domain for the tool's vendor, these network operations are considered safe and functional.- [PROMPT_INJECTION]: There is an indirect prompt injection surface in Phase A and Phase B, where user-supplied 'scene_description' is interpolated into the generation prompts. While this could allow a user to influence the image/video output beyond the intended 'premium' style, the risk is limited to the creative output of the generation models and does not pose a system security threat. Evidence: Ingestion point for 'scene_description' (SKILL.md); Capability inventory includes 'muapi' CLI calls and 'curl' network operations; no specific sanitization or boundary markers are defined for the prompt interpolation.
Audit Metadata