Security audit
Security checks for vulnerabilities and agentic risk
This is a document-processing skill that reads user-provided documents or URLs and creates summaries or reports, with no hidden execution, persistence, or exfiltration behavior found.
Before installing, expect the skill to read documents, webpages, and images you provide in order to summarize or analyze them. Avoid using it on sensitive files unless you are comfortable with the agent processing that content, and consider asking for confirmation before it handles ambiguous requests.
The manifest description and visible skill content are written as a Chinese-only experience, but there is no statement that the skill supports the user's preferred language or that Chinese is a justified locale constraint. This creates a natural-language policy concern because it implicitly fixes the interaction locale without user opt-in.
The auto-trigger conditions are broad phrases like '帮我看看', '分析', and '整理成文档', which can match many ordinary requests outside the intended scope. This can cause the skill to activate unexpectedly, leading to unnecessary access to uploaded files, URLs, or other content and increasing the chance of unintended data handling or skill routing mistakes.
No suspicious patterns detected.
