Vague Triggers
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The trigger list includes several broad natural-language phrases such as “话术分析” and “关系预警” that could plausibly appear in ordinary relationship or mental-health discussions, causing the skill to activate when the user did not explicitly intend to invoke it. This is not a code-execution issue, but unintended invocation can expose sensitive conversation context to a specialized analyzer and lead to confusing, privacy-impacting, or manipulative overreach in normal chats.
- Content
