brand-voice-enforcement
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the agent's text generation capabilities. It provides structured instructions for analyzing content requests and applying brand attributes.
- [DATA_EXPOSURE]: The skill attempts to read local configuration files (e.g.,
.claude/brand-voice-guidelines.md). This is the intended behavior for retrieving brand settings and does not target sensitive system files or user credentials. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from local files and session context to inform its output. While it lacks explicit boundary markers or sanitization for these inputs, the risk is negligible as the skill has no high-privilege capabilities such as network access, file writing, or command execution.
Audit Metadata