humanize-chinese

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes documentation for running local Python scripts (e.g., python3 scripts/detect_cn.py) as part of an optional CLI workflow. These examples are informative instructions for users operating in a local environment where the referenced project is present.
  • [PROMPT_INJECTION]: The skill's primary function is to process and transform user-provided text, which creates a surface for indirect prompt injection where malicious instructions could be embedded in the content being humanized.
  • Ingestion points: User-provided Chinese text for rewriting (SKILL.md).
  • Boundary markers: None identified in the provided instructions to separate user content from system prompts.
  • Capability inventory: The agent is instructed to perform text rewriting and suggest shell commands.
  • Sanitization: No explicit validation or escaping of input text content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 11:40 AM