humanizer-cli-detector

Fail

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation encourages downloading a zip file containing a Windows executable (humanizer.exe) from a third-party GitHub repository (0xwilliamortiz/humanizer-cli) that is not identified as a trusted source.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of unverified remote code by providing installation steps for a binary and a Node.js wrapper that triggers its execution.
  • [COMMAND_EXECUTION]: Several integration examples use child_process.execSync to run the downloaded binary, allowing the execution of arbitrary commands within the user's environment. This includes explicit instructions to override OS-level security protections like Windows SmartScreen and Antivirus quarantine.
  • [PERSISTENCE_MECHANISMS]: The skill describes how to integrate the external binary into git pre-commit hooks, ensuring that the code executes automatically during routine developer workflows.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 2, 2026, 12:44 AM
Security Audit — agent-trust-hub — humanizer-cli-detector