Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only Chinese creative assistant for brainstorming, naming, and concept ideas, with no code execution, privileged access, persistence, or hidden data handling.
Install this if you want a Chinese-language creative prompt assistant. Be aware that its activation phrases are broad and its guidance is not bilingual, so it may be less suitable if you expect English-first use or strict namespaced invocation.
The manifest description and user-facing usage section require Chinese phrases such as "头脑风暴", "起名字", and "创意设计" to use the skill. This effectively forces a specific language for activation and interaction, which matches the language/locale policy violation criteria because no opt-in, alternative language, or justification is provided.
The entire skill, including title, trigger phrases, prompt template, and example dialogue, is written only in Chinese and implicitly requires Chinese-language use. Under the policy, forcing a specific language without user opt-in or documented justification is a natural-language policy violation.
The trigger phrase includes very broad natural-language wording such as “帮我设计创意”, which can easily appear in ordinary conversation and cause the skill to activate unintentionally. In an agent setting, over-broad activation can route unrelated user input into this skill, causing confusion, incorrect task selection, or prompt-scope interference with other skills.
This markdown file defines activation phrases, so vague-trigger checks apply. While "起名字" is somewhat task-specific, "帮我起名" is a common conversational request and the file provides no narrowing context, exclusions, or negative examples to clarify when the skill should or should not activate.
Natural-language policy checks apply to all file types. The file presents the title, triggers, prompt template, and example dialogue only in Chinese, which may effectively enforce a single language without documenting user choice or a justified locale constraint.
No suspicious patterns detected.
