https://fresh-reads.lovable.app/What developers should know about, and what to do — from advisory databases and the researchers who find supply-chain malware.Sun, 01 Nov 2026 08:57:41 +0000https://www.wiz.io/blog/black-october-for-ai-developer-platforms866d4dd666d9f173Fri, 30 Oct 2026 22:51:44 +0000A series of agentic attacks on AI Developer Platforms has been leading to LLMJacking at scale. [confirmed · Wiz]ai-toolshttps://www.aikido.dev/blog/ai-agent-security-in-kubernetes-prompt-injection73225f6856d5a861Fri, 30 Oct 2026 19:31:00 +0000Abdel Sghiouar, Google engineer and senior cloud developer advocate, thinks prompt injection should be called prompt poisoning Category: Guides & Best Practices [confirmed · Aikido]ai-toolshttps://www.bleepingcomputer.com/news/security/malicious-claude-code-extension-on-cursor-planted-ssh-backdoors/f98c69bf43c7c459Fri, 30 Oct 2026 10:36:54 -0400A malicious version of Anthropic's Claude Code VS Code extension was distributed through Cursor's extension marketplace for approximately 11 hours on October 29, exposing up to 5,000 developers to malware designed to install persistent SSH backdoors. [...] [reported · BleepingComputer]ai-toolshttps://www.stepsecurity.io/blog/claude-code-extension-trojanizeda376c6814de942a8Fri, 30 Oct 2026 10:12:18 +0000On October 29, 2026, version 2.1.313 of the official Claude Code VS Code extension, anthropic.claude-code, was published with a malicious loader embedded in its extension.js bundle. The version was distributed through the Open-VSX registry and Cursor's extension marketplace, whic [confirmed · StepSecurity]ai-toolshttps://socket.dev/blog/claude-code-extension-compromise?utm_medium=feede8f44af938328989Fri, 30 Oct 2026 09:26:06 +0000Cursor removed a malicious Claude Code 2.1.313 extension from its marketplace. Socket examines registry records and the initial claims about its distribution. [confirmed · Socket]ai-toolshttps://thehackernews.com/2026/10/official-claude-code-vs-code-extension.html90688d3151e2bf62Fri, 30 Oct 2026 14:25:47 +0530Cybersecurity researchers have disclosed that a trojanized version of Anthropic's official Claude Code extension was distributed through the Cursor Marketplace as a legitimate update, attempting to install a persistent SSH backdoor on affected systems. The malicious update, versi [reported · The Hacker News]ai-toolshttps://www.bleepingcomputer.com/news/security/hugging-face-malware-campaign-returns-to-hijack-gpus-for-crypto-mining/ba3cd3eac5a72f80Thu, 29 Oct 2026 18:09:24 -0400A crypto-mining campaign abusing Hugging Face models returned days after takedown, hijacking GPU servers and planting backdoors, with one model downloaded over 28,000 times. Separately, a fake Solana starter kit on GitHub is positioned to trick AI coding agents into installing a [reported · BleepingComputer]ai-toolshttps://thehackernews.com/2026/10/fake-chatgpt-and-claude-apps-abuse.html9c56a02321bc491fThu, 29 Oct 2026 20:50:29 +0530Threat actors are delivering malicious loaders and cryptocurrency miners under the guise of artificial intelligence (AI) desktop applications for Anthropic Claude and OpenAI ChatGPT as part of a campaign dubbed Yoba. The activity involves creating fake GitHub projects that claim [reported · The Hacker News]ai-toolshttps://www.wiz.io/blog/the-rise-of-agentic-attacks4fbf402056f0c476Thu, 29 Oct 2026 14:26:22 +0000AI agents are changing how attackers operate. Explore real-world cases of agentic attacks, learn how to identify their fingerprints, and discover what they mean for the future of cybersecurity. [confirmed · Wiz]ai-toolshttps://www.bleepingcomputer.com/news/security/3-ways-ai-agents-already-operate-in-your-browser/814231d212d37a17Thu, 29 Oct 2026 10:00:10 -0400AI agents can control authenticated browsers, interact with corporate applications, and access sensitive data while appearing to act as legitimate employees. Keep Aware examines three ways agents operate inside browsers and why traditional security tools may struggle to distingui [reported · BleepingComputer]ai-toolshttps://www.bleepingcomputer.com/news/security/even-after-php2shell-blast-radius-matters-more-than-a-cvss-score/6b6cdecdf371b268Wed, 28 Oct 2026 09:50:59 -0400PHP2Shell shows how quickly attackers can exploit critical vulnerabilities, often before organizations have time to patch. Token Security explains why limiting the access of service accounts, API keys, and AI agents is just as important as fixing vulnerabilities to reduce the dam [reported · BleepingComputer]ai-toolshttps://www.aikido.dev/blog/aikido-launches-external-network-pentesting22b50db7ba9b16c9Wed, 28 Oct 2026 10:00:00 +0000Aikido launches external network pentesting: AI agents attack your internet-facing systems from the outside and report only findings they actually exploit. Category: Company Updates [confirmed · Aikido]ai-toolshttps://thehackernews.com/2026/10/cyberstrikeai-uses-44-ai-agents-to.htmlb0c9b44aa0625bf7Tue, 27 Oct 2026 23:56:46 +0530Cybersecurity researchers have disclosed details of three cyber attacks targeting organizations in Japan in which artificial intelligence (AI) was a key element, either in the driving seat or to assist a human operator. TrendAI, which analyzed three exposed server environments us [reported · The Hacker News]ai-toolshttps://www.bleepingcomputer.com/news/security/warp-discloses-breach-exposing-ai-agent-logs-user-telemetry-data/afa741ff67f996e3Tue, 27 Oct 2026 12:15:39 -0400Agent decision logs and telemetry data belonging to Warp agentic development environment users were exposed in an attack on a third-party vendor in the project's infrastructure. [...] [reported · BleepingComputer]ai-toolshttps://www.stepsecurity.io/blog/stepsecurity-now-inventories-ai-agent-plugins-in-your-github-repositories-and-on-developer-machinesf2ed444d9d8428acTue, 27 Oct 2026 11:23:27 +0000Inventory the Claude Code and Codex plugins on developer machines and in your GitHub repositories: where each came from, what it bundles, whether it is enabled, and which repositories distribute it. [confirmed · StepSecurity]ai-toolshttps://www.bleepingcomputer.com/news/artificial-intelligence/openai-launches-gpt-61-terra-with-3x-faster-ai-agents-50-percent-lower-pricing/c0fb63b7a262b30aMon, 26 Oct 2026 16:46:49 -0400OpenAI has launched GPT-6.1 Terra, a new model focused on computer use, visual reasoning, coding, and everyday work, while costing significantly less than its larger models. [...] [reported · BleepingComputer]ai-toolshttps://www.bleepingcomputer.com/news/security/when-an-ai-agent-is-the-incident-the-identity-record-is-the-evidence/c97e165df77c8891Mon, 26 Oct 2026 10:00:10 -0400A new NIST, CISA, and NSA guide treats runaway agents as incidents to be rehearsed. The hard part of the response is answering whose authority the agent used, and that answer has to exist before the incident does. [...] [reported · BleepingComputer]ai-toolshttps://thehackernews.com/2026/10/malicious-file-in-downloads-folder.html9b47e941f5afe803Mon, 26 Oct 2026 11:33:48 +0530A malicious instruction file sitting in a developer's Downloads folder tried to make their AI coding agent install a known-malicious npm package, security firm Forever Security said in a report published last week. The company caught the attempt on a real customer's machine and s [reported · The Hacker News]npmai-toolshttps://www.bleepingcomputer.com/news/security/ai-coding-agents-hijacked-using-agentsmd-file-in-downloads-folder/92c53c26133c7edcSun, 25 Oct 2026 11:49:38 -0400Researchers found a malicious AGENTS markdown instruction file in a customer's Downloads folder that tricked an AI coding agent into installing a rogue npm package. [...] [reported · BleepingComputer]npmai-toolshttps://thehackernews.com/2026/10/openai-ai-agents-demonstrate-vm-escapes.htmlf6239a8ec739144eSun, 25 Oct 2026 12:24:29 +0530OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of its most advanced AI models. "Based on the current state of alignment research, monitoring systems, and the sec [reported · The Hacker News]ai-toolshttps://thehackernews.com/2026/10/exposed-infrastructure-reveals-how.html03e531d5d591b16eFri, 23 Oct 2026 23:20:47 +0530Cybersecurity researchers have discovered an artificial intelligence (AI)-driven intrusion ecosystem run by affiliates of the INC and The Gentlemen ransomware groups. Central to the operation is an "Autonomous Red Team Kill Chain Framework" referred to as Phantom. The threat acto [reported · The Hacker News]ai-toolshttps://www.bleepingcomputer.com/news/security/you-gave-your-ai-agent-access-but-who-is-giving-it-orders/5f6d686ed2d4a1c8Fri, 23 Oct 2026 10:00:10 -0400AI agents can be manipulated through malicious emails, websites, and plugins into executing commands, stealing data, or deleting files using their legitimate permissions. Gen Digital explains how its Agent Trust Hub helps protect agents through skill verification, secure connecti [reported · BleepingComputer]ai-toolshttps://thehackernews.com/2026/10/critical-x402-sdk-flaw-could-let.html94c81b70f83f62c5Fri, 23 Oct 2026 14:05:45 +0530AI agents paying for API calls with the x402 SDKs could sign a payment for their full balance of a supported token if a malicious API asked for it, security firm V12 said on October 22. The cause was the SDKs' default client, which set no spending limit until releases on August 1 [reported · The Hacker News]ai-toolshttps://thehackernews.com/2026/10/the-ai-agent-nobody-owns-watch-expert.htmlb9c1e3e96f9a4e89Fri, 23 Oct 2026 00:35:35 +0530Right now, there is probably an AI agent running on a laptop somewhere in your network. It stores API keys and database passwords, can access your internal systems, and works without anyone watching. Nobody reviewed its access. Nobody owns it. If an employee had that much reach w [reported · The Hacker News]ai-toolshttps://www.wiz.io/blog/artex-in-the-wild-storm-0940-expands-targeting-of-it-and-software-vendorsffc4f7fb0cd497c6Thu, 22 Oct 2026 13:05:31 +0000Wiz Research is tracking an ARTEX-using actor, overlapping with Storm-0940, across multiple targeted software vendors. Learn how the AI agent attacks Okta, Entra, and Cognito, and what it left behind in the logs. [confirmed · Wiz]ai-toolshttps://thehackernews.com/2026/10/opencode-flaw-lets-malicious-mcp.html4b0824b45226c4b1Thu, 22 Oct 2026 16:14:05 +0530A flaw in the OpenCode AI coding agent allowed a malicious or hijacked MCP server to run code on a developer's Windows or WSL machine when the developer signed in. OpenCode connects to MCP (Model Context Protocol) servers to add outside tools, and such code would run with the dev [reported · The Hacker News]ai-toolshttps://thehackernews.com/2026/10/china-linked-hackers-use-artex-ai.htmlda9f7e6dd1b102c6Thu, 22 Oct 2026 09:51:26 +0530Microsoft on Wednesday disclosed that a China state-aligned actor dubbed Storm-0940 was behind the recent supply chain compromise of the ConnectWise Cloud Backup application. During the incident, Storm-0940 used ARTEX, a Go-based agentic AI penetration testing framework that was [reported · The Hacker News]ai-toolshttps://thehackernews.com/2026/10/the-harness-is-hard-part-of-agentic.html692eb73cab37d8dfWed, 21 Oct 2026 16:02:40 +0530An AppSec team can point an AI agent running on a general-purpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that makes those attacks safe to run against production and worth acting on afterward lives in the harness around the [reported · The Hacker News]ai-toolshttps://www.wiz.io/blog/from-phishing-to-llmjacking35f32033ba5ad8b5Tue, 20 Oct 2026 20:03:10 +0000How a single Google Search ad click leads to credential theft, hijacking of cloud billing account, and hundreds of thousands of dollars incurred in unauthorized AI API usage [confirmed · Wiz]ai-toolshttps://thehackernews.com/2026/10/hackers-use-autonomous-ai-agents-to.html0d98f0291d55c8e6Tue, 20 Oct 2026 19:37:17 +0530A Chinese-speaking criminal pointed autonomous AI agents at company websites and let them break in with almost no help, and a security researcher watched it happen because the operators left their control panels open on the internet. The agents tried more than 1,200 sites and rea [reported · The Hacker News]ai-tools