Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The skill is written entirely in Chinese and strongly constrains tone and interaction style without offering any language fallback or user-choice mechanism. This can exclude users who do not read Chinese, cause misunderstanding of safety boundaries, and lead the agent to respond in a language the user did not request, which is a real quality and accessibility risk even though it is not a classic security exploit.
