'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...
GitHub

A TACACS+ client that supports authentication, authorization and accounting.

Unlike RADIUS, which was designed for similar purposes, the TACACS+ protocol offers basic packet encryption but, as with most crypto designed back then, it's not secure and definitely should not be ...
Developer Tech

Socket: PyPI and npm payment SDK malware compromises CI/CD

According to Socket, malicious payment SDK packages on npm and PyPI are harvesting developer credentials and CI/CD ...

Fake Paysafe, Skrill SDKs on NPM and PyPi steal credentials

Malicious packages on the Node Package Manager (npm) and the Python Package Index (PyPI) delivered stealer malware to ...
The Hacker News

AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers

Sophos says Claude Code, Cursor, and Codex triggered Windows endpoint rules for credential access, LOLBin downloads, and ...
techtimes

First AI-Agent Ransomware Destroyed Data Even Payment Could Not Recover

a laptop screen with a webpage of the IT Army of Ukraine group of volunteer hackers. The IT Army of Ukraine first set up in the wake of Russia's devastating attack, and has since hugely grown in ...
winbuzzer.com

JADEPUFFER: The First Documented Agentic AI Ransomware Operation

Sysdig says JADEPUFFER may be the first agentic ransomware case, exposing how AI agents can turn old credential failures into database destruction. JADEPUFFER is a warning about exposed AI ...
Dark Reading

JadePuffer: The First Complete LLM-Driven Ransomware Attack

An "agentic threat actor" successfully exploited a Langflow flaw to steal data from a production database server and encrypt ...