Vague Triggers
Medium
- Confidence
- 87% confidence
- Finding
- The invocation guidance uses very broad natural-language triggers such as "scan," "handwriting," and "recognize text," which can overlap with ordinary conversation and cause the skill to activate in situations the user did not explicitly intend. In this skill, unintended activation is more concerning because the advertised workflow supports uploading local files or URLs to a third-party cloud OCR service, creating a risk of accidental data disclosure or unnecessary external processing.
