product-ad-video
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to interact with the Runware video inference API to create or edit videos based on product images. All external references and domains (runware.ai, vm.runware.ai) are associated with the vendor's infrastructure.
- [SAFE]: The skill includes a 'Brand-safety' section that instructs the agent to avoid generating invented claims, fabricated logos, or unauthorized on-screen copy, which is a defensive measure against misinformation.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file access or credential exposure was detected. The URLs used in the examples (example.com) are standard placeholders, and the video processing occurs via the vendor's own asynchronous task system.
- [PROMPT_INJECTION]: No patterns associated with prompt injection, role-play bypass, or safety guideline overrides were found.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute arbitrary code from external sources. It utilizes API calls for video inference, which is the intended and documented behavior of the skill.
Audit Metadata