Security audit
Security checks for vulnerabilities and agentic risk
This is a local Chinese text analysis skill with no network use, no persistence, and no evidence of hidden or destructive behavior.
Install only if you want Chinese AI-style detection and naturalness scoring. Be aware that broad trigger words may invoke it during general writing tasks, and file analysis reads the file path you provide locally.
The README explicitly frames the skill as a Chinese AI text naturalness detector and describes its purpose only for Chinese text. Under the policy criteria, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless clearly justified as region-specific; the document does not state such a justification or offer alternatives.
Without declared permissions the skill's intent is opaque and cannot be validated.
The trigger keyword at this line is broad enough to overlap with ordinary writing and editing requests, which can cause the skill to activate in contexts the user did not specifically intend. Overbroad auto-activation increases the chance of unintended file access or unnecessary processing of sensitive draft content, even if the skill itself is not overtly malicious.
Several trigger keywords in this range are generic terms like polishing, optimization, or writing style that are common across many benign assistant tasks. Such ambiguous triggers expand the activation surface, making accidental invocation more likely and creating unnecessary exposure of user text or local files to a skill that was meant for a narrower AI-text-detection use case.
The natural-language description explicitly defines the library as a Chinese AI text feature set, which imposes a language-specific scope. Under the policy rule for language/locale constraints, this should either offer user opt-in or clearly document why the Chinese-only restriction is required for a region- or language-specific purpose.
This Python file contains natural-language descriptions and CLI/help text entirely in Chinese, including the tool description and usage, with no indication that users can opt into another language. The policy requires flagging language or locale constraints when the skill forces a specific language without user choice or a clearly documented justification.
The package description states the tool is for optimizing and polishing Chinese AI text, and the categories/keywords reinforce a Chinese-only scope. Because the manifest does not indicate this language constraint as an optional user choice, it can be read as a language policy restriction without explicit opt-in.
