brand-voice

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to manage brand voice documentation and uses standardized methods for data ingestion and processing.
  • [SAFE]: Remote data fetching via WebFetch and Notion MCP is user-driven and limited to content extraction for synthesis into the style guide.
  • [SAFE]: Command execution is restricted to the skill's own local Python scripts for validation (voice_lint.py) and rule formatting (extract_rules.py).
  • [SAFE]: The skill implements safety measures such as preventing silent overwrites and requiring user confirmation before writing files.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found in the skill's instructions or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:29 AM