Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent AIEO monitoring helper, but it can collect and save screenshots, AI responses, analytics, and business conversion data under broad auto-trigger conditions without clear data-handling controls.
Install only if you intend to use it for Chinese-language AIEO monitoring. Before running browser automation or saving reports, confirm the brand, platforms, and questions to test; avoid capturing unrelated chat history, account details, customer records, CRM entries, ad account data, or unredacted analytics screenshots. Store the monitoring/ outputs where only the intended team can access them and delete old screenshots/reports when no longer needed.
The skill metadata and invocation description are written to operate in Chinese and specify only Chinese trigger phrases, with no indication that users may choose another language. This can violate a language/locale policy when a skill implicitly enforces one language without opt-in or explicit regional justification.
The skill metadata says it should auto-invoke on broad phrases like '效果监控' and '定期测试', which are generic and can match many unrelated requests. This can cause unintended activation of a skill with powerful tools including Bash, WebFetch, and browser automation, increasing the chance of unnecessary data access, browsing, or file creation.
The execution flow instructs collection of AI responses, screenshots, search trend data, website traffic data, and business conversion data, then stores reports under monitoring/ without any user-facing notice about data handling, consent, retention, or sensitivity. Because these datasets can include proprietary analytics or personal/business-sensitive information, silent collection and persistence creates privacy and governance risk.
The listed trigger keywords include highly ambiguous terms such as 'AI监控', '效果监控', '监控报告', and '品牌追踪', which are not uniquely tied to this skill. In context, accidental invocation is more dangerous because the skill is designed to collect external data, read prior reports, take screenshots, and write monitoring artifacts.
The entire template is written in Chinese, including headings, field labels, and status text, and it does not indicate that another language may be used or that Chinese is required for a specific regional purpose. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The guide explicitly instructs users to capture screenshots and record AI responses as evidence, but it provides no privacy, retention, redaction, or consent guidance. Because the monitored platforms may contain account identifiers, chat history, user prompts, or other sensitive business data, this can lead to unintentional collection and storage of sensitive information in the monitoring/ directory.
This markdown template forces a specific language/locale for all report content, headings, labels, and placeholders. Under the policy, language constraints should either offer a user choice or be clearly documented as justified for a region-specific use case, which this file does not do.
This markdown template forces a specific language/locale for all user-facing instructions and labels. Under the policy, locale-specific language should either be optional, user-selectable, or clearly justified as region-specific.
This markdown file contains user-facing natural-language guidance exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this locale. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
The document presents all operational instructions in Chinese and does not offer a language option or explain that the skill is intended only for a Chinese-speaking or region-specific audience. This can be a natural-language policy issue when a skill effectively forces a specific language without user opt-in.
No suspicious patterns detected.
