Vague Triggers
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The natural-language triggers are broad enough to overlap with ordinary conversational requests like asking the assistant to greet someone, which can cause the skill to activate unintentionally. This is not code-execution dangerous, but it can lead to misrouting of user intent, unexpected skill invocation, and reduced reliability of the agent’s behavior.
- Content
