Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed Chinese-language military news aggregation skill that searches public news sources and does not request local, persistent, credential, or code-execution access.
Install this only if you want Chinese-language military news roundups. Expect the agent to perform multiple public web searches and fetch news pages; no local data or credentials are requested by the skill.
The trigger description is broad enough to activate on general questions about current events or geopolitics, not just narrowly scoped military-news requests. That can cause the skill to overtake user intent, perform unnecessary browsing, and surface sensitive conflict-related content when the user did not clearly ask for this specialized workflow.
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 this is not a code-execution or data-exfiltration issue, it is still a behavioral safety problem because it forces an output mode the user may not understand.
This markdown file is entirely written in Chinese and presents the resource list and search guidance only in that language. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale limitation is explicitly documented and justified, which is not present here.
No suspicious patterns detected.
