Pipelab vs Island Security

Pipelab

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.

Island Security

Attackers are spoofing big brands to get your AI agent to install malware. Island Security Research uncovered 7,600 malicious GitHub repositories — over 800 posing as AI Skills or MCP servers — with some using Walmart, Databricks, Gmail, Salesforce, Spotify, and other big brand names to look legitimate. The payload: SmartLoader and the StealC infostealer, with 14M+ downloads.