Security audit
Security checks for vulnerabilities and agentic risk
This is a simple research-helper skill whose disclosed examples fit its purpose and do not show hidden or unsafe behavior.
Before installing, understand that using the examples may send search or fetch requests to external services and may run local commands if you ask the agent to do so. Review commands and URLs before execution, but no hidden install-time or persistent behavior was found.
The skill explicitly demonstrates external web requests and local code execution, but provides no warning that these actions may transmit user data to third parties, access untrusted remote content, or cause system-side effects. In an agent-skill context, such omissions can mislead users into invoking sensitive operations without understanding privacy, security, or execution risks.
The natural-language description and headings are primarily in Chinese, and the file does not indicate that language selection is optional or that the skill is intentionally limited to a Chinese-language audience. The policy for SQP-3 flags forced language or locale behavior when there is no opt-in or documented justification.
