Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only interaction-design workflow skill with no executable code, hidden actions, credential handling, or destructive behavior.
Before installing, check that this skill is intended for Chinese-language Agent interaction design work and that any implementation of page-context access, operation-log checks, template sharing, or submit flows remains user-confirmed and scoped to the active product workflow.
The trigger description uses broad phrases like “交互设计”, “Agent 流程”, and routing from a generic workflow-start path, which can cause this skill to activate in contexts the user did not intend. In an agent system, unintended invocation can override more specific skills, mis-handle user requests, or expose contextual data to an interaction-design workflow that was not meant to run.
The skill description and operating instructions are entirely in Chinese and do not indicate that users may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.
No suspicious patterns detected.
