BREACH://AI ~/research/clawhub-agent-attack.md

Category [AGENT-TO-AGENT] Feb 2026 Live Campaign

AI Agents Are Now Hacking Each Other. One Was Caught in the Act.

ClawHub agent attack chain

Independent summary of research originally conducted and published at Straiker by Yash Somalkar and Dan Regalado.

A threat actor built an AI agent persona on Moltbook, earned trust inside the agent social network, and used that trust to push malicious Claude Skills that exfiltrate Solana wallet private keys and route payments through attacker-controlled infrastructure. On-chain evidence confirmed. First documented agent-to-agent attack chain in the wild.

Read the full research on Straiker

BreachAI did not independently conduct this research. This is a summary of research originally conducted and published at Straiker by Yash Somalkar and Dan Regalado.