Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Developer Fernando Irarrázaval's AI agent experiment drew over 6,000 hack attempts from more than 2,000 attackers. No one ...
Though the breach occurred at a third-party service provider, hackers used that access to steal LastPass customers' contact ...
Three class-action lawsuits accuse a hacking group of publishing data that included personal and corporate information stolen ...
OpenAI is rolling out the full, limited-release version of GPT-5.5-Cyber—a specialized AI model that outperforms its ...
ThreatsDay Bulletin: Claude Chat Abuse, NastyC2 npm Packages, Device-Code Phishing + 25 More Stories
ThreatsDay Bulletin covers AI abuse, poisoned packages, phishing, macOS attacks, SD-WAN flaws, scams, and supply-chain ...
Python based backdoor that uses Gmail to exfiltrate data as an e-mail attachment. This RAT will help someone during red team engagements to backdoor any Windows machines. It tracks the user activity ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results