brand-voice
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation and strategy tool. It does not perform network operations, access sensitive file paths, or execute shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for auditing existing brand copy, creating a data ingestion surface.
- Ingestion points: The skill requests "5 to 10 examples of existing brand writing" and audience descriptions in
SKILL.md. - Boundary markers: None provided in the instructions.
- Capability inventory: None; the skill does not utilize any tools for file writing, network access, or command execution.
- Sanitization: None; the agent processes raw text provided by the user.
- Note: This surface is considered safe because the skill lacks the capabilities required to weaponize malicious input.
Audit Metadata