The company’s alternate-universe internet serves as a massive sandbox that allows the Chrome team to properly train AI browsing agents—without the risk of them going rogue.
The easiest way to fool someone is to give them something they already expect. A job offer. A message about a service outage. A familiar app. Nothing looks strange at first. And that's the problem. This week's stories show how ordinary things are being used to steal data, spread malware, and get people to hand over…
Shopify's AI agent system that continuously attacks their production infra, list of open-source offensive AI agent harnesses, la creme de la cloud 2026
Artex and similar penetration testing tools allow newbie hackers to scan targeted systems for vulnerabilities and successfully wage attacks using prompts fed to chatbots.
External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this project with Prime…
View CSAF Summary Mendix Studio Pro contains multiple vulnerabilities in the MCP Server, that could allow an attacker with network access to interact with the server remotely or trick a user's browser into sending unauthorized requests, potentially leading to unauthorized data access, tool execution, or system…
Two AI agents, separately over a five-day period, autonomously tried to access connected applications, including Google Calendar, Gmail, Slack, and GitHub, without account owner permission.
Apple on Monday introduced new controls that allow Mac users to give more granular access to data they give to apps, including those that use artificial intelligence (AI) agents. The changes, currently previewed in macOS 27.3 beta 2, relate to increased transparency and more options for two of its APIs: Device…
Google on Monday revealed that adversarial use of artificial intelligence (AI) by threat actors has gone beyond manual prompting to deploying autonomous multi-agent offensive frameworks like ARTEX, CAIRN, CyberStrikeAI, and PentAGI to execute multi-stage intrusions at greater operational velocity. In tandem, threat…
Attackers' AI agents have been hunting for weak spots in internet-exposed AI apps such as LiteLLM, One API, and Dify to steal the AI provider keys stored inside, according to the agents' own records. The records, which Amazon's threat intelligence team captured with decoy servers, describe stolen keys being used to…
Is Cursor AI safe? Privacy Mode covers your data, but Cursor calls its agent guardrails best effort. Six risks, the settings to change and the controls to add.
24 GenAI security resources for November 2026: a cross-tenant leak on Workers AI, a Hugging Face malware campaign that came back, and three vLLM flaws.
MCP security in November 2026: a reference server leaks secrets to any web page, SDK responses cross clients, and FastMCP sends secrets to rogue OAuth servers.