write
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions (SKILL.md) include robust security and privacy boundaries, such as forbidding the invention of facts/quotes, protecting private contact information, and explicitly requiring separate authorization for publishing or sending content. It emphasizes a 'draft-only' default behavior.
- [SAFE]: The skill operates entirely through text instructions and referenced markdown files for formatting and style guides. There are no executable scripts, external package dependencies, or network operations found in the provided files.
- [SAFE]: The project uses standard YAML configuration for agent metadata and static SVG assets for the UI, with no evidence of obfuscation or malicious redirection.
Audit Metadata