Vague Triggers
Medium
- Confidence
- 88% confidence
- Finding
- The trigger descriptions are very broad (e.g., plant photos, plant name inquiries, care questions, diagnosis requests), which can cause the skill to activate for many ordinary plant-related conversations without clear user intent to invoke this specific skill. In an agent ecosystem, over-broad activation can route users into unintended behavior paths, reduce predictability, and create opportunities for prompt/context hijacking through accidental invocation.
