Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent brand-analysis prompt with an optional simple Python scoring snippet and no evidence of hidden access, persistence, or destructive behavior.
Install this if you want a Chinese-market brand personality analysis helper. Be aware that it may answer in Chinese by default and may use web search or simulated semantic estimates for brand traits, so treat its numeric outputs as analytic approximations rather than verified measurements.
The README presents the skill entirely in Chinese and instructs users to invoke it in that mode without offering any language choice or fallback. This can exclude or mislead users who operate in other languages, increasing the risk of misunderstandings about outputs, consent, and appropriate use, though it is not a direct code-execution or data-exfiltration issue.
The skill instructs the agent to operate in Chinese and frames the role and output protocol entirely in Chinese without offering any user choice. This can override a user's preferred language, reduce accessibility, and create prompt-priority conflicts where the agent follows the skill's language constraint rather than the user's explicit request.
No suspicious patterns detected.
