ugc-hot-girl
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a static instruction set for generating text-based prompts. It lacks any functionality for system interaction, network requests, or sensitive file access. \n- [PROMPT_INJECTION]: The instructions are designed to guide the AI in creative writing and do not attempt to bypass safety guidelines or override system instructions. While the skill possesses an indirect prompt injection surface as it processes user input into downstream prompts, it is for a benign purpose. \n
- Ingestion points: User preferences for character attributes (age, ethnicity, product context) entering the context in SKILL.md. \n
- Boundary markers: None identified in the provided instructions. \n
- Capability inventory: Mentions downstream tools for automated image and video generation (
/higgsfield-image-auto,/seedance-auto-generate). \n - Sanitization: No explicit sanitization or validation of user-supplied text is described.
Audit Metadata