Vague Triggers
Medium
- Confidence
- 86% confidence
- Finding
- The manifest description includes very broad trigger phrases such as 'reviews,' 'case studies,' and 'social proof,' which can cause the skill to activate in contexts where the user did not actually request testimonial-generation help. Over-broad activation is dangerous because it can misroute user intent, override a more appropriate skill, or inject irrelevant guidance into unrelated workflows, especially in multi-skill agent environments.
