Lucene search
+L

4 matches found

Kitploit
Kitploit
•added 2026/10/09 2:09 a.m.•15 views

Agent-Security-Regression-Harness

OWASP 智能体安全回归测试框架 OWASP 智能体安全回归测试框架是一个开源、厂商中立的测试框架,用于针对智能体应用和集成 MCP 的系统运行可执行的安合回归测试场景。 该项目帮助构建者和防御者验证对提示词、模型、工具、检索来源、记忆、审批流程或 MCP 集成的更改不会重新引入已知的安全故障。 该项目的作用 该项目提供了一个以代码为先的测试框架,用于: 运行可复现的智能体安全滥用案例场景 通过策略断言验证预期的安全结果 为本地开发和 CI 生成机器可读的结果 捕获执行追踪以用于调试和审计 为智能体和 MCP 安全风险构建可复用的场景库 该项目不是什么 该项目不是: 基准测试 扫描器...

6.3AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/10/05 7:39 p.m.•9 views

security-harness

安全测试框架 一个面向 Claude Code(以及后续其他 AI 代理)的多代理应用安全审查框架 。一个路由技能会调度到完整的攻击性安全流水线,该流水线会映射 代码库、利用按类别划分的知识库搜寻 漏洞、将发现串联 成升级路径、验证 真实影响,并报告 为 README / JSON / SARIF / 文档 / PDF。 范围:此框架对您拥有或获授权测试的代码执行静态 分析(源代码审查、数据流追踪、PoC/载荷构造)。它不会攻击实时第三方系统。 包含内容 security-harness/ a plugin marketplace └── plugins/security-harness...

6.3AI score
SaveExploits0References5
Packet Storm News
Packet Storm News
•added 2026/08/13 12:00 a.m.•30 views

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

The expanding operational capabilities of large language model LLM agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses...

5.8AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
•added 2026/05/12 10:00 p.m.•117 views

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

9.8CVSS7AI score0.01619EPSS
SaveExploits3
Rows per page
Query Builder