ChatGPT's new Lockdown Mode can stop prompt injection - here's how it works ...
OpenAI launches Lockdown Mode and Elevated Risk warnings to protect ChatGPT against prompt-injection attacks and reduce data-exfiltration risks.
The module targets Claude Code, Claude Desktop, Cursor, Microsoft Visual Studio Code (VS Code) Continue, and Windsurf. It also harvests API keys for nine large language models (LLM) providers: ...
The malicious version of Cline's npm package — 2.3.0 — was downloaded more than 4,000 times before it was removed.
Cline CLI 2.3.0 was published with a stolen npm token, installing OpenClaw in an 8-hour attack affecting ~4,000 downloads.
A hacker tricked a popular AI coding tool into installing OpenClaw — the viral, open-source AI agent OpenClaw that “actually does things” — absolutely everywhere. Funny as a stunt, but a sign of what ...
Palo Alto Networks’ Unit 42 says two critical flaws are being actively abused to gain unauthenticated access, deploy persistent backdoors, and compromise entire enterprise mobile fleets even after ...
A critical vulnerability in Grandstream GXP1600 series VoIP phones allows a remote, unauthenticated attacker to gain root privileges and silently eavesdrop on communications.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results