minimalist-product-ad-generator
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, including product images and advertising copy, which are then used to generate prompts for video and image generation models.\n
- Ingestion points: User-provided product images and ad copy are ingested in 'Step 1: Asset Check' and 'Step 5: Generate or Confirm Apple-style English Copy' within SKILL.md.\n
- Boundary markers: The skill lacks explicit instructions for the agent to ignore or sanitize potential commands embedded within user-provided visual or text assets, though it utilizes a structured extraction process.\n
- Capability inventory: The skill has access to powerful generative tools including MiniMax-H3 for video, music-2.6 for audio, and potentially ElevenLabs for voice synthesis.\n
- Sanitization: There is no evidence of specific sanitization or filtering of user-provided content before it is interpolated into generation prompts.
Audit Metadata