Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only learning skill that gives structured study guidance and does not request sensitive access or run code.
Installers should expect this skill to take over many Chinese concept-learning prompts and produce a multi-perspective deep explanation. Use it when that default behavior is desired; it does not add code execution or sensitive system access.
The trigger phrases are extremely broad (e.g. 'X 是什么', '讲讲 X', '理解 X'), which can cause the skill to activate for many generic educational requests rather than a clearly scoped niche. In an agent system, over-broad routing increases the chance of misinvocation, bypasses more appropriate specialized skills, and can lead to irrelevant or lower-quality handling of user intent.
The natural-language instructions and examples are entirely Chinese, which can imply a fixed language/locale behavior. There is no explicit opt-in, language selection mechanism, or justification that this skill is intentionally region- or language-specific.
Declaring the skill as the 'default entry' for broad learning requests creates ambiguous boundaries and encourages it to supersede other skills whenever the user asks to understand a concept. That kind of default catch-all behavior is risky in orchestration because it can dominate routing decisions and make agent behavior less predictable or controllable.
No suspicious patterns detected.
