{"skill":{"slug":"sx-self-safety-guard","displayName":"sx-self-safety-guard","summary":"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。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":194,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1773639434381,"updatedAt":1777526100524},"latestVersion":{"version":"1.0.0","createdAt":1773639434381,"changelog":"**Major update: Introducing AI自我安全防护系统 v2 with multi-layered defense and comprehensive protection modules.**\n\n- Upgraded to version 2.0.0 with 8 independent defense modules covering prompt injection, identity verification, system prompt protection, supply chain attacks, credential theft, malicious code, sensitive data, and abnormal behaviors.\n- Implements a 4-layer boundary check (input, tool call, memory, output) for deep protection—each layer can intercept risky requests.\n- Introduces a 5-level risk assessment with adjustable scoring and tailored response protocols for each threat.\n- Clearly separates core responsibilities between self-safety-guard (runtime request blocking) and SX-security-audit (environment file/config scan).\n- Enhances user interaction with context-aware warnings, confirmation flows, and explanatory responses matched to risk levels.\n- Comprehensive detection and response logic for evolving attack patterns such as multi-turn attacks, privilege escalation, and cross-channel social engineering.","license":"MIT-0"},"metadata":null,"owner":{"handle":"zhuxiaobao-y","userId":"publishers:zhuxiaobao-y","displayName":"zhuxiaobao-y","image":"https://avatars.githubusercontent.com/u/242132972?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.prompt_injection_instructions"],"summary":"Detected: suspicious.prompt_injection_instructions","engineVersion":"v2.4.5","updatedAt":1777526100524}}