Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Markdown-only website analytics helper; its privacy documentation is thin, but the behavior is disclosed and proportionate to the stated purpose.
Before installing, treat this as a Chinese-language analytics/reporting helper and provide only data you are authorized to analyze. For real user analytics, prefer aggregated or anonymized metrics and add your own privacy, consent, and retention rules because the skill does not define them.
The skill description and usage examples are entirely in Chinese and present the assistant as a Chinese-language tool, but they do not state that language is optional or user-selectable. This can violate language/locale policy when a skill effectively requires a specific language without opt-in.
The example trigger phrases are generic user requests such as traffic analysis and conversion optimization, which are likely to overlap with ordinary conversation. In agent-routing environments, this can cause unintended skill activation, broad interception of user queries, and misrouting of requests away from more appropriate tools or default handling.
The skill explicitly supports user behavior analysis, geographic distribution, and path tracking, which can involve personal or sensitive behavioral data, but it provides no privacy notice, consent expectations, or data-handling constraints. This increases the risk of misuse, non-transparent profiling, and privacy compliance issues when operators use the skill on real user data.
The natural-language content and examples are fully Chinese, which effectively imposes a language/locale on users. The policy allows this only when the skill offers language choice or clearly documents a justified region-specific constraint, neither of which appears here.
This markdown file contains user-facing content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the language/locale policy, forcing a specific language without user choice can be a natural-language policy violation.
No suspicious patterns detected.
