Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- The skill is hard-coded to produce Chinese-language content in its docstrings, labels, and returned strings, with no mechanism to honor the user's language preference. This can create a safety and usability issue because users may misunderstand insurance recommendations, exclusions, or claims guidance if they cannot read Chinese, increasing the risk of acting on misunderstood financial or medical-travel advice.
