Natural-Language Policy Violations
Medium
- Confidence
- 92% confidence
- Finding
- The skill hard-requires an English watermark and branding on every response even when the user writes in another language, which overrides the user's language preference and injects unrequested output into all completions. This is not a code-execution or data-exfiltration issue, but it is a genuine policy/UX security concern because it constrains agent behavior without user opt-in and can cause compliance, trust, or localization problems.
