Filter

×
Active Filters Clear All
Keyword: 开源安全 ×
4 Total Reports
Microsoft Technology Update 2026-05-22

Microsoft Open-Sources RAMPART & Clarity: CI-Driven Red Teaming and Multi-AI Design Validation for Agents

Microsoft open-sources RAMPART, an agent red-teaming framework that encodes attack scenarios into repeatable CI tests, and Clarity, a structured design validation tool using multi-AI perspectives. Together they form a spec-driven AI security engineering loop, aiming to lower enterprise costs and drive standardization.

Cisco Other Medium Signal 2026-04-01

Cisco Launches Open-Source AI Agent Security Solution DefenseClaw

Cisco released open-source security solution DefenseClaw with four protection engines for OpenClaw AI Agent, covering prompt inspection, tool detection, installation scanning and code review. The solution demonstrates defense against 11.9% identified threats including malicious skills and unsafe MCP servers through hands-on labs.

NVIDIA Other High Signal 2026-03-23

NVIDIA Launches OpenShell Open-Source Runtime for AI Agent Security Isolation

NVIDIA introduces OpenShell open-source runtime providing system-level sandbox isolation for autonomous AI agents, separating application operations from infrastructure policy enforcement. Partners with Cisco, Google Cloud to establish unified runtime policy management. Releases NemoClaw reference stack for simplified deployment.

Cisco Other Medium Signal 2026-03-13

Cisco Open Sources RAG Vector Space Security Detection Tool

Cisco releases open source Adversarial Hubness Detector tool with multi-detector architecture to identify adversarial attacks in RAG vector spaces, supporting major vector databases. Extends defense from prompt layer to knowledge retrieval layer against emerging 'gravity well' attacks.