brand-voice
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected in the skill file.
- [SAFE]: The skill ingests data from .agents/brand-context.md without explicit boundary markers or sanitization. However, because the skill lacks capabilities such as subprocess execution, network operations, or file-writing across all components, the security risk of indirect prompt injection is minimal.
- [PROMPT_INJECTION]: No behavioral overrides, safety bypass instructions, or system prompt extraction patterns were detected in the skill instructions.
Audit Metadata