The Hacker News AI Security ยท June 11, 2026

New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets

Why it matters

Two security teams have shown, in separate research published this week, that OpenClaw, the popular self-hosted AI agent, can be driven to run attacker-controlled code or hand over sensitive data through ordinary-looking inputs. Imperva buried instructions inside shared contacts, vCards, and location pins that the agen

My takeaway: New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.