Natural-Language Policy Violations
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill is written to enforce a Chinese-language and persona-specific response style without presenting language choice or user consent. This can reduce user control, cause inaccessible or confusing output for non-Chinese users, and create mismatches between user intent and assistant behavior, especially when the skill is activated indirectly.
- Content
