Vague Triggers
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill advertises extremely broad trigger phrases such as generic references to 'AI news' and even '今天发生了什么' when the context is AI-related, which can cause unintended invocation. Overbroad routing can send user prompts and context to an external service when the user did not clearly request it, creating privacy, consent, and integrity risks in agent behavior.
- Content
