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

Read full story on The Hacker News
Share
New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets
AI disclosure

Summary

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

Original reporting

Open original source

Related coverage

Read full article on The Hacker News

Get the AFBytes Brief

Major stories, AI-assisted analysis, and what to watch next. Free, monthly, unsubscribe anytime.