A newly disclosed weakness in Anthropic's Claude Code lets a malicious repository quietly load files from outside a project and ship their contents to a remote server on the tool's very first request — no user approval or explicit tool call required. The issue, detailed by researchers at Tego, centers on Claude Code's memory import feature and a mismatch between how the tool checks file paths and how it actually reads them.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.