Share story
Security AI

Researcher reports Claude Code Auto Mode exploit chain

Researcher reports Claude Code Auto Mode exploit chain Image: Primary
A security researcher reported a lab attack chain that led Claude Code Opus 5 in Auto Mode from a website-summary task to execution of a remote test payload, with observed 60% to 80% success rates in a small sample. The reported chain used a downloaded archive and Python module shadowing after the agent wrote and ran its own decoder. The researcher said Anthropic closed the disclosure as informative and described Auto Mode as a convenience feature, with OS isolation and network-egress controls as the security boundary.
Sources
embracethered.com
In this story
Anthropic
Published by Tech & Business, a media brand covering technology and business. This story was sourced from embracethered.com and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
Infrastructure Capital
Infrastructure Capital

Nscale faces Norway data center delays while seeking up to $3 billion IPO

AI infrastructure firm Nscale is seeking to raise up to $3 billion in an initial public offering as soon as this month, Bloomberg reports. Construction of its flagship Norwegian data center has faced regulatory hurdles, a fire and...

Bloomberg Technology
Security AI
Security AI

Preprint reports 97% accuracy classifying software supply chain threats

Researchers report 97% accuracy and 97% macro F1 for a GPT-4 framework that classifies open-source software supply chain threats into five attack categories. Their preprint uses 999 verified incidents spanning 2018 to 2026 across ...

cs.CR updates on arXiv.org
AI Science
AI Science

Researchers report lower-cost training for LLM information gathering

Researchers report in a preprint that training language models to select questions using information-gain rewards improved performance on Twenty Questions at substantially lower computational cost than the experimental-design base...

cs.LG updates on arXiv.org