Security audit
Security checks for vulnerabilities and agentic risk
This is a simple web-research guidance skill with no code, persistence, credential access, or hidden behavior, though users should be aware it favors Chinese-language sources by default.
Install this if you want an agent to structure web research and cross-check sources. For global, legal, medical, security, or highly technical topics, ask the agent to prioritize authoritative sources in any language rather than Chinese-language sources by default.
The trigger conditions are broad enough that the skill may activate for many generic requests involving searching, verification, or feasibility checks. This can cause unintended invocation, leading the agent to perform web access or apply this skill when the user did not clearly request it, increasing the risk of scope creep, irrelevant browsing, or policy bypass through unexpected tool use.
Hard-coding a preference for Chinese-language resources without user opt-in can bias retrieval quality and completeness, especially when the most authoritative or current materials are in other languages. In a web-research skill, this may systematically suppress better sources and distort results, which is a security-relevant reliability issue when users depend on accurate external information.
