Vague Triggers
Medium
- Confidence
- 95% confidence
- Finding
- The trigger list is excessively broad and includes generic terms such as "Memoir," "identity," "Jewish," "Black," "church," "education," and even users saying they just installed the skill or do not know how to start. This can cause unintended activation in unrelated conversations, leading the agent to inject off-topic content or override more relevant routing, which is a real security and safety concern in agent ecosystems even without malicious intent.
