Categories: The Verge

The AI security nightmare is here and it looks suspiciously like lobster

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 to come as more and more people let autonomous software use their computers on their behalf.

The hacker took advantage of a vulnerability in Cline, an open-source AI coding agent popular among developers, that security researcher Adnan Khan had surfaced just days earlier as a proof of concept. Simply put, Cline’s workflow used Anthropic’s Claude, which could be fed sneaky instructions and made to do things that it shouldn’t, a technique known …

Read the full story at The Verge.

rssfeeds-admin

Share
Published by
rssfeeds-admin

Recent Posts

Pluralistic: No one wants a permanent gerontocracy (15 May 2026)

Today's links No one wants a permanent gerontocracy: The one policy everyone agrees on. Hey…

1 hour ago

How AI Can Fix Africa’s Unreliable Grids

For the past two decades, electrification has been central to Africa’s development agenda. Although nearly 600 million…

1 hour ago

How AI Can Fix Africa’s Unreliable Grids

For the past two decades, electrification has been central to Africa’s development agenda. Although nearly 600 million…

1 hour ago

The Detection-Evasion Arms Race Is Quietly Reshaping How Teams Use AI Writers

If you spent the last two years building any kind of content workflow on top…

1 hour ago

The Detection-Evasion Arms Race Is Quietly Reshaping How Teams Use AI Writers

If you spent the last two years building any kind of content workflow on top…

1 hour ago

Founder of Gremlin Discusses the Need for AI Guardrails

Businesses around the world are starting to think about the importance of security in the…

1 hour ago

This website uses cookies.