Vague Triggers
Medium
- Confidence
- 91% confidence
- Finding
- The README states the skill activates automatically for broadly phrased requests like fact verification or cross-checking, but does not clearly constrain scope, required user intent, or safety boundaries. Overly broad activation can cause the skill to trigger in unintended contexts, potentially routing sensitive, ambiguous, or higher-risk requests into web search/fetch workflows without sufficiently specific user consent or task narrowing.
