Pipelab

About

No description available.

Ad copy example

Introducing Agent Egress Bench, an open-source test corpus for security tools that sit between AI agents and the network, covering 197 logical cases across 18 categories including secret exfiltration, prompt injection, SSRF, hostname exfiltration, MCP tool poisoning and chain detection, MCP drift, A2A protocol scanning, WebSocket DLP, encoding evasion, shell obfuscation, and crypto/financial DLP.