Latest cybersecurity reporting from selected sources.

Per usual, there's no fix – or even any documentation – for GitLost

Cybersecurity researchers have disclosed details of a now-patched critical session isolation vulnerability in Writer, an enterprise generative artificial intelligence (AI) platform, that could result in cross-tenant compromise

New Microsoft research shows how attackers can hijack AI agents that act on a user's behalf, using nothing more than a poisoned tool description to make the agent quietly hand over company data to an outsider

Researchers tested 444 AI chatbot apps for iPhone and found that 282 of them, nearly two-thirds, exposed paid AI access through their network traffic

Convince an AI browser that it is playing a game, and it can hand over your login details. That is the finding behind BioShocking, a technique from security firm LayerX that tricked six AI browsers and assistants into copying a user's credentials and sending them to an attacker

LayerX tricked AI browsers including ChatGPT Atlas and Comet into bypassing their guardrails

OpenAI appears to be testing a new subscription and experience for science use cases, but it's unclear if it'll be available to everyone regardless of their background. [...]

FulcrumSec leaked data stolen from Novo Nordisk, claiming to have exfiltrated 1.3TB, including clinical records and AI research assets. On June 15, 2026, a data-theft extortion group calling itself FulcrumSec began leaking files from Novo Nordisk, the Danish maker of Ozempic and Wegovy, after the company refused a $25 million ransom demand. The attackers claimed […]

The Gentlemen ransomware used infostealer credentials, AI tools, and affiliates to hit 483 victims across 66 countries in under a year. The Gentlemen surfaced as a ransomware operation in September 2025 and by June 13, 2026 had listed 483 victims on their dark-web leak site, 380 of them in 2026 alone. That makes them the […]

Two security teams have shown, in separate research published this week, that OpenClaw, the popular self-hosted AI agent, can be driven to run attacker-controlled code or hand over sensitive data through ordinary-looking inputs

It's been one of those weeks. You expect the usual noise: recycled malware, sloppy attacks, another easy target getting hit. Instead, there's a supply chain attack kit in a public repo, a $5,000-a-month RAT that clones browsers, and research showing AI agents can be tricked into leaking real credentials

Monday again. The weekend was meant to be quiet. It wasn't. Last week had poisoned packages, a broken AI helper, and a worm tearing through repos. The ugly part: basic tricks still worked

Sloppy AI-generated npm infostealer leaked its own GitHub token, exposing the operator

This week starts small

Monday opens with a trust problem. A mail server flaw is under active use. A network control system was targeted. Trusted packages were poisoned. A fake model page pushed a stealer. Then came the familiar ransom claim: the data was returned and deleted

The TeamPCP hacker group is threatening to leak source code from the Mistral AI project unless a buyer is found for the data. [...]

Exposed UIs, weak authentication, and risky defaults could turn cloud-native AI apps on Kubernetes into potential targets by threat actors. Learn how exploitable misconfigurations lead to RCE and data leaks. The post When configuration becomes a vulnerability: Exploitable misconfigurations in AI apps appeared first on Microsoft Security Blog.

Blames outfit called Context.ai, which reckons an agentic OAuth tangle caused the incident Vercel, the company that created the open source Next.js web development framework, has a data leak that led to compromise of some customer credentials, and blamed an outfit called Context.ai for the mess.…

Two recently fixed prompt injections in Salesforce Agentforce and Microsoft Copilot would have enabled an external attacker to leak sensitive data.

By hiding malicious instructions on an attacker-controlled Web page, AI could ingest orders that appear benign but return sensitive data to the attacker's server.