🤖 AI Agent Supply-Chain Malware in Instruction Files

Mitiga Labs scanned 50,000+ AI instruction files across 7,000+ repos, finding prompt-exfiltration malware, ANTHROPIC_BASE_URL MITM overrides, YOLO-mode permission bypasses, and 1,230+ hardcoded API keys. They released Skillgate, a free scanner, to detect these techniques.

https://www.mitiga.io/blog/malware-in-ai-instruction-files-skillgate

#AI