minimalist-product-ad-generator
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill implements a strictly controlled workflow with mandatory user checkpoints for assets, copy, and storyboards, ensuring the agent does not perform significant actions without oversight.
- [SAFE]: Tool references such as MiniMax-H3, Seedance, and music-2.6 are appropriate for the creative nature of the skill and represent the vendor's established infrastructure.
- [SAFE]: Thorough analysis of the instructions and metadata confirmed the absence of data exfiltration, credential exposure, or unauthorized command execution patterns.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it processes untrusted user assets. 1. Ingestion points: User-provided images and text strings in SKILL.md. 2. Boundary markers: The agent performs intermediate analysis (Fact Summary) and creates a brief, though it lacks explicit technical delimiters. 3. Capability inventory: High-capability video and music generation tools invoked in SKILL.md. 4. Sanitization: Manual review checkpoints and the translation of user copy to English serve as practical sanitization layers.
Audit Metadata