humanizer-zh
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
- Ingestion points: The skill processes external, potentially untrusted text provided for editing and review through the Read tool.
- Boundary markers: The instructions do not provide explicit boundary markers or directives to ignore instructions embedded within the text to be processed.
- Capability inventory: The agent is authorized to use the Write and Edit tools, which allows it to modify file contents based on its processing of the input text.
- Sanitization: There is no evidence of input validation or sanitization to filter out malicious prompts embedded in the source text.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no inclusion of Python scripts, Node.js code, or package management files.
Audit Metadata