Tag: openclaw
2 articles
AI Agents Vulnerable to Phishing Attacks, Expose Sensitive Data
Researchers put an AI agent named Pinchy to the test with classic phishing simulations, and the results were alarming: sometimes it fell for the bait, spilling sensitive data, and other times it successfully blocked the attacks. The experiment revealed a stark vulnerability - AI agents can be tricked into exposing confidential information.
OpenClaw Flaws Expose Data, Enable Privilege Escalation
A chain of four vulnerabilities, dubbed Claw Chain, in OpenClaw can be exploited to turn an agent into a powerful tool for attackers, allowing them to extract sensitive data, escalate privileges, and plant backdoors for long-term access. This flaw chain enables adversaries to gain a foothold, move undetected, and wreak havoc on an OpenClaw-managed environment.