30 fake AI Chrome extensions caught stealing passwords and more

Security experts have uncovered dangerous Chrome extensions that promise or impersonate AI tools to steal sensitive data.

ChatGPT's new Lockdown Mode can stop prompt injection - here's how it works

The new security option is designed to thwart prompt-injection attacks that aim to steal your confidential data.

Password managers’ promise that they can’t see your vaults isn’t always true

All eight of the top password managers have adopted the term “zero knowledge” to describe the complex encryption system they use to protect the data vaults that users store on their servers. The ...
eWeek

OpenAI Introduces New Safeguards in ChatGPT to Prevent AI Prompt Injection

OpenAI launches Lockdown Mode and Elevated Risk warnings to protect ChatGPT against prompt-injection attacks and reduce data-exfiltration risks.
SecurityWeek

Password Managers Vulnerable to Vault Compromise Under Malicious Server

Researchers at ETH Zurich have tested the security of Bitwarden, LastPass, Dashlane, and 1Password password managers.

Infostealer malware found stealing OpenClaw secrets for first time

With the massive adoption of the OpenClaw agentic AI assistant, information-stealing malware has been spotted stealing files ...

Passwords to passkeys: Staying ISO 27001 compliant in a passwordless era

Password-based authentication is increasingly risky as organizations adopt passkeys to strengthen security and meet ISO/IEC 27001 requirements. Passwork explains how to align passwordless adoption ...