Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Chinese-language reference skill with broad trigger wording but no executable behavior, persistence, credential use, or high-impact authority.
Install only if you want a Chinese-language prompt/reference for this super-search topic. Be aware that the generic '冷知识' trigger may activate in unrelated Chinese conversations, but the inspected artifact does not show unsafe authority or hidden behavior.
The trigger includes the broad term "冷知识" without constraints, which can cause the skill to activate in many unrelated conversations. Overbroad activation can hijack user intent, inject irrelevant behavior, and increase the chance that the agent applies this skill in contexts where it was not requested.
The trigger scenarios are loosely defined (e.g. user says "冷知识" or needs related help), making activation criteria ambiguous. This increases the risk of unintended invocation, which can interfere with normal assistant behavior and cause the skill to respond outside its intended scope.
The skill metadata and trigger phrases are entirely Chinese, and the file does not offer any language choice or note that the skill is intended only for a Chinese-speaking context. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy issue.
