Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed helper for creating and managing user-requested SubAgents, with broad agent-spawning capability but no hidden code, exfiltration, or system persistence found.
Before installing, understand that this skill helps create other agents that may be given read, write, web, or command execution abilities. Use run mode for short tasks, reserve session mode for cases where persistence is needed, and review or limit each SubAgent's task and tools before letting it work on sensitive data.
The manifest description is entirely in Chinese and presents the skill's activation/use guidance in that language only. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
The markdown content, including usage instructions, triggers, workflow steps, and examples, is consistently written in Chinese with no indication that users may choose another language. This can violate language/locale policy because it implicitly requires a specific language without documented opt-in or justification.
The natural-language instructions, parameter descriptions, and examples are all presented in Chinese, and the file does not indicate that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
No suspicious patterns detected.
