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

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

Notícia de segurança recolhida automaticamente.

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 agent executed without the victim ever seeing them. Varonis built a test agent on

Fonte original: Ler artigo completo aqui