Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple Chinese-language character sheet prompt template with no code execution, data access, persistence, or hidden behavior.
Install this if you want a Chinese-language helper for generating structured character reference prompts. Be aware that broad phrases like character design or draw a character may trigger it, and non-Chinese users may find the interface and outputs inaccessible unless the agent adapts language on its own.
The trigger phrases listed in the description are broad everyday terms such as “画角色” and “人物设计”, which can easily appear in normal conversation and cause the skill to activate unintentionally. Unintended invocation can override user expectations, route requests into the wrong behavior, and increase the chance of prompt/response confusion in multi-skill environments.
The skill content is written entirely in Chinese and frames the interaction around Chinese-language trigger phrases and output conventions without indicating any user language selection or fallback behavior. This can cause misrouting, user confusion, or inaccessible behavior when invoked in other language contexts, though it is primarily a usability and safety-boundary issue rather than a direct security exploit.
The display name, short description, and default prompt are all written only in Chinese, which can impose a specific language on users without explicit opt-in. The policy requires flagging language or locale constraints when the skill does not offer a user choice or clearly justify the restriction.
No suspicious patterns detected.
