write
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions and reference files. There are no shell commands, scripts, or automated tool invocations present.
- [SAFE]: The
SKILL.mdfile defines a clear operational scope (writing/editing prose) and uses relative file paths to load its own reference documents (references/write-zh.mdandreferences/write-en.md). These references contain purely stylistic guidelines, vocabulary suggestions, and tone instructions. - [SAFE]: There are no patterns of prompt injection, data exfiltration, or persistence mechanisms. The skill specifically warns against restructuring documents without permission and emphasizes preserving the user's intended meaning.
Audit Metadata