Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Tom's Hardware on MSN
AI coding agents can be tricked into installing malware via 'clean' GitHub repositories
Three levels of indirection, all with seemingly innocuous steps, will catch a bot off-guard.
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
(C) 2016-2022 by Mathematics and Computer Science (MCS), Argonne National Laboratory. See COPYRIGHT in top-level directory. Kindly note: This site contains the implementation of SZ2.x. The most ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results