Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese AI-news research helper that uses broad web searching, with no evidence of hidden execution, persistence, credential access, or destructive behavior.
Install this if you want a Chinese-language AI news briefing workflow that will perform many web searches and read external sources. Users who prefer another output language or fewer searches may need to adjust the skill instructions before use.
The trigger description uses broad, natural-language phrases like asking for 'today's AI news' or 'what's hot recently,' which can cause the skill to activate in many ordinary AI-related conversations without clear scoping. Over-broad activation increases the chance of unintended invocation, unnecessary web access, and response hijacking away from the user's actual intent.
The skill mandates Chinese output regardless of the user's language preference, which can override user intent and reduce transparency or usability for non-Chinese-speaking users. While not a direct code-execution risk, forced language output is a control-boundary issue that can mislead users and interfere with safe, comprehensible responses.
This markdown file presents all instructions and descriptions in Chinese only, including headings, annotations, and search guidance. Under the policy rule for language or locale constraints, forcing a single language without user opt-in can be a natural-language policy violation unless the regional limitation is explicitly justified.
No suspicious patterns detected.
