Security audit
Security checks for vulnerabilities and agentic risk
This skill appears benign: it creates Word documents with a disclosed AI-disclaimer footer and does not show hidden access, exfiltration, or persistence.
Before installing, note that the skill is written for Chinese-language use and generated documents default to a Chinese AI-disclaimer footer unless changed. It can create directories and write DOCX files at paths requested by the user, and it can embed image files the user points it to.
The manifest description and the entire user-facing documentation are written in Chinese, and there is no indication that users may choose another language or that the skill is intended only for a Chinese-speaking or region-specific context. This creates a natural-language locale policy concern because the skill implicitly fixes the interaction language without opt-in.
This code's user-facing natural-language documentation, validation errors, and status messages are entirely in Chinese, which imposes a specific language/locale by default. Under the policy, forcing a specific language without offering a user choice or documenting a justified locale constraint is a natural-language policy violation.
No suspicious patterns detected.
