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 ...
All payloads use api: "every" meaning they are available to every customer, not restricted by API key. The earliest payload dates to November 2024, proving the operation has been actively maintained ...
This project uses RecaptchaDomainReplicator (from recaptcha-domain-replicator) to build the local replica page and launch the browser session. It creates a new replicator, starts a local HTTPS server, ...
Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results