humanizer
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and documentation. There are no scripts (Python, Node.js, Shell, etc.) provided or executed by this skill.
- [PROMPT_INJECTION]: The skill instructions define an 'editor' persona to humanize text. While it uses strong instructional language (e.g., 'You are a writing editor', 'Your Task'), these are legitimate configurations for the agent's behavior and do not attempt to bypass safety filters or extract system prompts.
- [DATA_EXFILTRATION]: There are no commands or code patterns that attempt to access sensitive files or perform network operations. The
allowed-toolssection inSKILL.mdrestricts the environment, and the instructions themselves focus strictly on text transformation within the chat context. - [EXTERNAL_DOWNLOADS]: The README provides standard
git cloneinstructions for manual installation into specific directories. The skill itself does not perform any automated downloads or package installations during operation.
Audit Metadata