
AgentGuard
Zero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…
ai-securitycontainer-securitydefensive-tools+2
8

Zero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…

Policy engine and EDR for AI agent fleets and developer workstations. Monitors tool calls, file access, network flows, and process execution with…

getshell test

Open-source sandboxed runtime for AI agents — gVisor/Docker isolation, credential vault, immutable audit log. Built after CVE-2026-25253.

Exploit for CVE-2019-5737, a Docker runc container escape vulnerability, with build and run instructions for Linux and Windows.