Vague Triggers
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The activation instruction says users can 'directly describe the current application scenario' to trigger the skill, but it does not define scope boundaries, required confirmations, or limits on autonomous actions. In a skill that later describes network access, material generation, and handling of enterprise application data, this can cause the agent to begin collecting, processing, or acting on sensitive information without clear user consent or constrained execution.
- Content
