Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward design-to-code guidance skill with no executable code, persistence, credential handling, or hidden high-impact behavior.
Install this if you want an agent to implement frontend UI from design artifacts. Be aware that the documentation is primarily Chinese and the trigger conditions are broad, so users may want to invoke it explicitly for design-to-code tasks.
The skill metadata and instructions are primarily Chinese-oriented and imply Chinese-language interaction without stating that language should follow user preference. This can override or bias the agent's response language, leading to user confusion, miscommunication, or incorrect handling of requirements in multilingual environments.
The activation criteria are broad enough to trigger on generic phrases like 'implement from design' or the presence of a screenshot/link, which can cause the skill to auto-invoke in situations where the user did not clearly request this specialized behavior. In an agent setting, ambiguous auto-invocation can route tasks to the wrong capability, causing unintended code generation, context misuse, or unsafe downstream actions based on unverified design inputs.
The skill's title, trigger section, and example invocations are written entirely in Chinese, and the manifest description mixes Chinese trigger phrases without indicating that other languages are supported. This creates a natural-language locale expectation that may exclude users who do not opt into Chinese, which matches the language/locale policy concern.
The skill name, tagline, and description are written entirely in Chinese, which imposes a specific language on users in the manifest-visible text. There is no indication that the skill is region-specific or that users can opt into another language, matching the language/locale policy concern for natural-language content.
No suspicious patterns detected.
