SECURITYBLEEPING COMPUTER
OpenClaw AI agent found falling for phishing attacks, spills user data
The OpenClaw AI agent was found to be vulnerable to phishing attacks during simulations, leading to user data exposure. Testing with various configuration profiles revealed susceptibility to tactics commonly used against human users.
Related Signal
Adjacent reporting
- Robinhood account creation flaw abused to send phishing emails
- New FBI warning reveals phishing attacks hitting private chats
- Malicious Web Pages Are Hijacking AI Agents, And Some Are Going After Your PayPal
- Toxic Combinations: When Cross-App Permissions Stack into Risk
- ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface
- A spyware investigator exposed Russian government hackers trying to hijack Signal accounts