Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed Chinese-language perspective/roleplay skill for smart-car and autonomous-driving analysis, with no executable code or privileged behavior.
Install only if you want a Chinese-language He Xiaopeng-inspired analysis style for smart-car topics. Use explicit prompts when invoking it, and treat first-person answers as roleplay based on public information rather than actual statements or predictions from He Xiaopeng.
The trigger list includes broad phrases such as general discussion of smart cars, autonomous driving deployment, and product definition. This can cause unintended activation during normal conversation, leading the agent to switch personas or apply this skill when the user did not explicitly request it, which may override safer or more relevant behavior.
This markdown file presents all user-facing content in a single language and does not indicate that the skill is region-specific or that users may opt into another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructional/content text exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language.
The skill states that once activated it will respond in He Xiaopeng's first-person perspective and fixed style, without offering user language or format choice. This can reduce user control, create misleading impersonation-style output, and make the assistant less transparent about when it is roleplaying versus providing neutral analysis.
No suspicious patterns detected.
