humanizer

Warn

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The README.md file encourages users to install the skill by cloning a repository from an external GitHub account (https://github.com/blader/humanizer.git) that is not identified as a trusted vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite text provided by users or read from the file system, which could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The skill ingests text through user interaction and by using Read, Grep, and Glob tools to scan files as specified in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the content to be humanized and instructions within that content.
  • Capability inventory: The skill has access to sensitive tools including Read, Write, Edit, Grep, Glob, and AskUserQuestion across the file system.
  • Sanitization: The skill does not implement any validation or sanitization of the input text before processing it.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 18, 2026, 06:33 AM
Security Audit — agent-trust-hub — humanizer