Security audit
Security checks for vulnerabilities and agentic risk
This is a simple summarization skill that may be overly rigid, but it does not request sensitive access, run code, persist changes, or handle credentials.
Install this if you want a very terse three-sentence summary style. Avoid relying on it when you need detailed analysis, safety caveats, legal or financial nuance, or an answer in a specific format or language.
The trigger phrases are broad, conversational, and overlap with common user requests such as '结论是什么' and '简单说说', so the skill may activate when the user did not specifically intend to invoke this exact behavior. In a summarization skill, unintended activation can suppress needed nuance or safety-relevant detail by forcing content into a rigid three-sentence compression format.
The trigger descriptions are extremely broad and match common summarization phrases like TL;DR or 'what's the conclusion,' which can cause the skill to activate in many ordinary contexts where the user did not specifically want this rigid three-sentence behavior. Overbroad activation can hijack normal assistant behavior, leading to unintended summarization, loss of important nuance, and failure to follow more appropriate task-specific instructions.
The usage section lists ambiguous conditions like 'simple explanation' or 'what is the conclusion,' which overlap with many normal requests that may need richer answers than a forced three-sentence summary. This ambiguity increases the chance of accidental activation and inappropriate truncation of content, especially where precision or completeness matters.
The skill imposes a fixed output structure and Chinese-oriented constraints without offering a language or formatting choice, which can override user preferences and system behavior. In practice, this can produce the wrong language, overly compressed answers, or mismatched formatting, reducing reliability and potentially hiding important caveats by forcing strict brevity.
No suspicious patterns detected.
