brand-voice-writer
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts with internal vendor-specific tools (e.g.,
get_marketing_context,search_content) to retrieve documentation and writing samples. These operations are consistent with the skill's intended function and do not involve unauthorized external data access. - [SAFE]: It includes a dedicated step to load a 'No Fly List', which acts as a security and privacy filter to prevent the AI from mentioning restricted customers in public-facing marketing material.
- [SAFE]: No patterns of prompt injection, obfuscation, or credential harvesting were detected. The instructions provided are focused on maintaining brand consistency and avoiding typical AI writing artifacts.
Audit Metadata