Security audit
Security checks for vulnerabilities and agentic risk
This skill is a small Chinese-language note about using search, with broad triggers but no executable code, persistence, credential access, or data-changing behavior.
Before installing, note that this skill may activate on broad Chinese terms and its content is minimal. It appears safe from a security perspective, but the publisher should narrow the triggers for better control.
The trigger includes very broad generic terms such as "冷知识", which can match many unrelated user requests and cause the skill to activate outside its intended context. Over-broad activation increases the chance of unintended instruction injection, user confusion, and inappropriate skill execution in unrelated conversations.
The activation conditions are vague (e.g. trigger on users saying "deep-search" or "冷知识"), which makes it easy for the skill to run in ambiguous or unrelated situations. This weak scoping can expose users to unintended behavior and increases the attack surface for prompt-trigger abuse or accidental invocation.
The skill description, triggers, and usage instructions are entirely in Chinese, with no indication that users can choose another language or that the locale restriction is intentional and documented. This may violate language/locale policy if the environment expects neutral or user-selectable language behavior.
