Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- The skill explicitly limits output to simplified Chinese only, without indicating any fallback to the user's preferred language. This can cause the agent to ignore user language needs and degrade usability, potentially leading to misunderstanding of disclaimers, advice, or limitations. In this horoscope context it is not a direct security exploit, but it is still a real quality/safety issue because it forces behavior that may conflict with user intent.
