Vague Triggers
Medium
- Confidence
- 95% confidence
- Finding
- The trigger list is overly broad and includes generic terms such as 'essays,' 'contrarian,' 'literary criticism,' and onboarding phrases like 'doesn't know how to start,' which can cause the skill to activate in unrelated conversations. This creates an unintended prompt-injection surface and poor routing behavior, where the assistant may enter the skill context when the user did not intend to invoke it.
