Cybersecurity
Agent Security
AI Agent 系统安全测试方法论。当目标系统使用 AI Agent 执行工具调用、多 Agent 协作、 或自主决策时触发。覆盖 OWASP Agentic AI Security Top 10 (ASI01-ASI10): 目标劫持、工具滥用、身份权限、供应链、代码执行、记忆投毒、多 Agent 通信、 级联故障、人机信任利用、失控 Agent。
- Publisher / source
- wgpsec/AboutSecurity (found on GitHub top repositories)
- Upstream record
- wgpsec/AboutSecurity
- Version
- Version 1
- Published
- Publication review
- Approved for publication
- Content fingerprint
51951bfc1711923926c501465a01abf4597144f022bff0bda3dda18c6311a0a9