brand-voice-evaluation
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats detected. The skill's primary function is to read a local reference file and evaluate text consistency.
- [DATA_EXFILTRATION]: Accesses the style guide at
@{AGENT_FOLDER}/dockit/references/style-guide.md. This is a non-sensitive internal resource required for the skill's operation and does not involve exfiltration to external domains. - [PROMPT_INJECTION]: Processes external documentation for evaluation. While the documentation is untrusted data, the skill lacks high-privilege capabilities such as command execution or network access that could be exploited via indirect injection.
Audit Metadata