Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Chinese-language skill that estimates whether text sounds AI-written and does not request tools, credentials, persistence, or system access.
Install this if you want Chinese-language, style-based AI-writing estimates. Treat its percentages as rough opinions only, not as plagiarism results, academic integrity evidence, or output from a professional AI-detection service.
The file’s user-facing instructions are entirely in Chinese and provide no alternative language or indication that the skill is region-specific. This can violate a language/locale policy when users are not given a choice or informed of the locale constraint.
The trigger examples are broad natural-language phrases for a generic text-analysis task, which increases the chance that this skill is invoked when the user intended a different workflow. In a multi-skill environment, ambiguous activation can cause scope confusion, misleading outputs, or accidental interception of prompts better handled by another tool.
The specific trigger phrase 'AI查重' is ambiguous because it commonly refers to plagiarism or similarity checking rather than stylistic AI-generation estimation. This can misroute users into a skill that explicitly does not perform real database comparison, creating misleading expectations and incorrect task handling.
No suspicious patterns detected.
