Vague Triggers
Medium
- Confidence
- 91% confidence
- Finding
- The example triggers are broad natural-language phrases such as asking to generate a cover, check balance, or view history, without documenting tight activation boundaries or confirmation requirements. In an agent setting, this can cause over-broad invocation, leading the skill to activate unexpectedly and send user prompts or account-related requests to an external service, which increases privacy and unintended-action risk.
