writing-humanizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious behavior detected. The skill consists of Markdown documentation and prompts intended for text transformation.
- EXTERNAL_DOWNLOADS (LOW): The installation instructions direct users to clone a repository from an untrusted GitHub account (
blader/humanizer). While not a 'Trusted Source', the repository appears to contain only Markdown configuration for the agent and no executable code was identified in the analyzed files. - INDIRECT_PROMPT_INJECTION (LOW): The skill's primary function is to process and 'humanize' untrusted user-provided text. This is a known surface for indirect prompt injection, though the risk is minimized as the skill lacks dangerous capabilities like file-system writes or outbound network requests in the provided context.
Audit Metadata