Skills
skills/brycewang-stanford/auto-empirical-research-skills/humanize-chinese/Gen Agent Trust Hub

humanize-chinese

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the exec tool to run local Python scripts such as detect_cn.py and humanize_cn.py located within the scripts directory. This is consistent with its stated purpose of providing a local text processing toolchain.
  • [EXTERNAL_DOWNLOADS]: The documentation references installation commands via GitHub and NPM. These are recognized as trusted, well-known services and are used here for legitimate software distribution purposes.
  • [DATA_EXFILTRATION]: No unauthorized data transmission or network activity was identified. The skill's primary focus is local text analysis, and it specifically highlights its ability to function without an internet connection or external LLM API dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 11:31 AM
Security Audit — agent-trust-hub — humanize-chinese