
sandbox
Run untrusted AI code safely, fast
api-securitycloud-securitycontainer-security+3
1968 months ago

Run untrusted AI code safely, fast

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Top-level repository for LFI: Practical, Efficient, and Secure Software-based Sandboxing

GO sandbox to run untrusted code

CVE-2020-0890 | Windows Hyper-V Denial of Service Vulnerability proof-of-concept code

Proof-of-concept demonstrating a Node.js permission model bypass (CVE-2026-21636) that allows network access via undici/fetch to local services,…