blog-brand
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to facilitate the creation of brand and voice documentation. It functions by interviewing the user and persisting the responses to local files.
- [DATA_EXPOSURE]: The skill reads and writes files (
BRAND.mdandVOICE.md) in the local project root. This is the intended purpose of the skill to provide persistent editorial context across different sessions. - [PROMPT_INJECTION]: The skill manages editorial rules and voice constraints. While these instructions are intended to influence future agent behavior, the information is gathered directly from the user and stored in the project's local environment, which is standard for context-setting skills.
Audit Metadata