tamv-brand-voice
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill integrates comprehensive safety and governance modules (tamv-core-governance, tamv-rights-safety-guard) to manage risk and consent. It explicitly forbids the imitation of other brands or people and provides instructions for minimizing personal data exposure.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs to generate content.
- Ingestion points: Processes user-provided values, examples, and audience descriptions in SKILL.md.
- Boundary markers: Includes instructions to treat drafts as data and not instructions.
- Capability inventory: Performs logging to an authorized registry and transfers output to a quality gate.
- Sanitization: Uses dedicated safety guard modules to filter content.
Audit Metadata