Security audit
Security checks for vulnerabilities and agentic risk
This is a simple summarization prompt skill with no code, commands, persistence, credentials, or external data transfer.
Installers should expect this skill to help format summaries and meeting notes. If language consistency matters, ask the agent to answer in your preferred language when using it.
The skill description uses very broad trigger phrases for generic summarization tasks, which can cause the agent to invoke this skill in many common contexts without clear boundaries. Over-broad activation increases the chance of unintended routing, context capture, or interference with more specific skills, especially when users ask ambiguous questions.
The usage examples include highly generic phrases like 'summarize this' and 'extract key points' without disambiguation, making accidental or excessive activation likely. In an agent environment, this can degrade intent routing reliability and cause the skill to process content outside its intended scope.
The skill is largely written in Chinese and presents Chinese headings and output templates, but it does not state that language should follow the user's preference. This can amount to an implicit language constraint without an explicit opt-in or locale justification.
No suspicious patterns detected.
