Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Chinese-language BI report generator that analyzes user-provided data snippets and does not request privileged access, persistence, network activity, or code execution.
Install this if a Chinese-language BI-style report format is acceptable. Redact personal, financial, or confidential fields before pasting data, because the skill is designed to analyze whatever sample rows the user provides.
The skill name, description, and usage guidance are presented entirely in Chinese, which creates a natural-language locale constraint. The file does not indicate that Chinese is optional, user-selectable, or required for a documented region-specific purpose.
The example cases and validation rules strongly constrain outputs to Chinese-language phrasing and specific Chinese section headers without any indication that this is optional or user-configurable. In a general-purpose BI skill, this can override user preference, create prompt steering behavior, and cause reliability or policy-compliance issues when downstream systems expect locale-neutral or user-selected output.
The natural-language metadata and parameter descriptions are entirely in Chinese, with no indication that language is selectable or that the skill is intended only for a Chinese-speaking or region-specific context. This can violate language/locale policy when a skill implicitly forces one language without user opt-in or documented justification.
The manifest description and user-facing instructions are written exclusively in Chinese, which can impose a fixed language on users without an explicit opt-in or locale justification. The policy requires flagging language or locale constraints when the skill forces a specific language without user choice.
This manifest-style JSON describes the skill's purpose in broad terms but does not define when the skill should or should not be invoked, nor does it provide specific trigger phrases or exclusion conditions. For manifest files, missing specificity around activation can lead to unintended invocation overlap with other general data-analysis requests.
No suspicious patterns detected.
