Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
In 2025 and 2026, several independent sources have highlighted the same trend: Prompt injection remains one of the most ...
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
Developer Fernando Irarrázaval's AI agent experiment drew over 6,000 hack attempts from more than 2,000 attackers. No one ...
Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...
Mastra AI’s 144 JavaScript packages was executed in just 88 minutes by North Korea’s Sapphire Sleet hacking group, which ...
A Nevada family is suing Roblox, alleging the gaming platform let their child be groomed by an adult and failed to provide ...
Instructure, the company behind the educational tool Canvas, has struck a deal with the hacking group ShinyHunters. This agreement secures stolen student and school data. ShinyHunters confirmed data ...
App and website hosting giant Vercel on Thursdays said hackers had accessed some of its customers’ data before the company discovered its recent data breach, suggesting that this incident may have ...
One employee at Vercel adopted an AI tool. One employee at that AI vendor got hit with an infostealer. That combination created a walk-in path to Vercel’s production environments through an OAuth ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results