minimalist-product-ad-generator

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or metadata. The skill follows a strict multi-step workflow with user checkpoints and uses platform-integrated tools for media generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-uploaded product images and advertising copy to generate content. This ingestion of external data constitutes a standard indirect prompt injection surface for this type of application.
  • Ingestion points: User-provided product images and ad copy specified in the 'Start Gate' section of SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or 'ignore embedded instructions' warnings for the ingested data.
  • Capability inventory: The agent utilizes video generation (MiniMax-H3), music generation (music-2.6), and audio track manipulation capabilities.
  • Sanitization: The skill includes instructions for localization and length validation of text copy but lacks explicit security sanitization for adversarial content potentially embedded in uploaded images or text strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 02:58 AM