domains / families / security / sx-self-safety-guard

sx-self-safety-guard

separate

AI自我安全防护系统v2。多层防御：提示注入、身份冒充、系统提示泄露、 过度代理、供应链攻击、凭证窃取、恶意代码、敏感数据泄露、行为异常检测。 触发词：安全防护、身份验证、prompt injection、system prompt、 权限升级、MCP安全、self-safety-guard、安全检查。

When to use

• prompt injection detection
• identity verification
• system prompt protection
• excessive agency detection
• supply chain and MCP security
• credential theft detection
• malicious code detection
• sensitive data leakage prevention

When not to use

• executing security scans
• modifying system configuration
• accessing the network
• storing credentials
• overriding verified owner decisions

Skill page

Source