brandkit
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language art-direction instructions and internal prompt templates. No executable scripts, binary files, or network-active commands were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied brand names and reference descriptions. While this provides an entry point for untrusted data, the instructions require the agent to 'infer strategy' and follow a rigid template, effectively isolating the input within an artistic context. The capability is limited to text-to-image generation prompts, presenting minimal risk.
Audit Metadata