Beam / field notes
Loading…
BetaBeam / field notes
Loading…
Beam / field notes
What we're seeing as we watch AI coding agents work — flagged actions, skill/MCP scan findings, and how to keep Claude Code, Codex, and the rest honest without slowing them down.Page 4 of 21
245 posts
Oct 31, 2026 · 11 min readBlack October: Wiz Links Nine AI Platform Breaches to LLMjacking of Stolen KeysWiz says at least nine AI developer platforms disclosed incidents in October, nearly all hunting stored environment variables. Its new data shows two enterprise keys from those breaches turning into hundreds of thousands of resold model calls within days.
Oct 31, 2026 · 11 min readChainalysis Says an Attacker Used "Offensive Agentic Techniques": What Is Confirmed and What Is NotOn October 30, 2026 Chainalysis said an external actor used "offensive agentic techniques" to reach its systems and internal tools, exposing user IDs, names, emails and role labels. This post separates what the company stated from what is still unknown, and covers what customers and engineering teams should do.
Oct 31, 2026 · 10 min readChatGPT Share Link XSS: How One Shared Chat Could Run Code in Your SessionA public ChatGPT share link could run attacker JavaScript inside the signed-in session of anyone who opened it. Here is the chain, the fix OpenAI shipped on October 26, and what it teaches anyone who opens AI transcripts.
Oct 31, 2026 · 9 min readVOLTA Infostealer Uses an LLM to Rank Victims: What Talos Found and What Developers Should CheckCisco Talos described VOLTA on October 31, 2026: a self-deleting Windows infostealer that feeds stolen data to an LLM through OpenRouter and gets back a ranked profile of what the victim is worth. It also takes SSH keys and cloud configuration, which sit on every developer machine. This post covers the chain, what is confirmed, and what to change.
Oct 30, 2026 · 11 min readAur0ra Ransomware Operators Used Cursor Agents to Reach Domain Admin: What Sophos FoundSophos Counter Threat Unit says the group behind Aur0ra ransomware used Cursor agents, backed by Anthropic, xAI and Moonshot models, to move from stolen credentials to domain administrator in victim networks. This post walks through the attack chain, what is confirmed, the indicators, and what it means for anyone who runs coding agents.
Oct 30, 2026 · 9 min readBinance Security Incident: Compromised DevOps Laptop, $6.3 Billion Estimated Impact, Withdrawals SuspendedOn October 30, 2026 Binance said a security incident may involve a compromised DevOps engineer laptop that was used to reach a service container and submit unauthorized withdrawals. It puts the potential impact at about $6.3 billion, says about $3 billion is frozen, and has suspended deposits and withdrawals. This post separates what Binance stated from what outlets estimated, and covers what users and engineering teams should do.
Oct 30, 2026 · 17 min readClaude Code VS Code Extension 2.1.313 Compromised: SSH Backdoor, Up to 5,000 Users, How to Check and Clean UpCursor says a modified build of the Claude Code VS Code extension, version 2.1.313, was served from its extension marketplace on October 29, 2026 and affected at most 5,000 users. The loader adds an attacker SSH key labeled svc-telemetry, installs persistence and beacons host details to a server. Anthropic did not build it. This post gives the check commands, the indicators, the cleanup order and what is still unknown.
Oct 30, 2026 · 7 min readDHS Employee Data Leak: 40,000+ Records, a Disputed Okta Claim, Claimed vs VerifiedA hacktivist group calling itself Department of Peace says it took personnel data on more than 40,000 Department of Homeland Security employees and contractors from an Okta single sign-on service, and Distributed Denial of Secrets published it on October 28, 2026. Okta says it has no evidence its systems were compromised, and DHS says it is aware of a potential breach. This post separates verified facts from claims and covers what identity teams should check.
Oct 30, 2026 · 10 min readEmbrace: Embedded-Browser Flaws in Cursor, Copilot, Claude Desktop, Codex and VS CodeForever Security reports that the browsers built into five AI coding assistants share one design flaw: they relax normal browser rules to serve the agent. Two bugs are fixed, one is partly acknowledged, and file reads in Codex and VS Code are reported as unpatched. Here is the mechanism, the timeline and what to do.
Oct 30, 2026 · 10 min readGitLab CVE-2026-97229 Exploited: CISA KEV, CVSS 10 CI/CD Regex RCE and What to RotateCISA added GitLab CVE-2026-97229 to its Known Exploited Vulnerabilities catalog on October 29, 2026, with a federal deadline of November 1. The CVSS 10 flaw lets an unauthenticated user run code on self-managed GitLab through a crafted CI/CD regular expression. This post covers the affected versions, the fixed releases, the six detections GitLab published, and the credentials a compromised server exposes, including those held by coding agents.
Oct 30, 2026 · 10 min readHugging Face trust_remote_code Miner Campaign Returns, and a Fake Solana Kit Targets Coding AgentsTwo separate campaigns show the same weakness: code that runs because something you trust chose it. Pluto Security tracked a Hugging Face miner campaign that came back after takedown, and Air Security described a GitHub repo that ranks first when an agent looks for a Solana starter kit. Here is the mechanism and what to check.
Oct 30, 2026 · 13 min readn0n Ransomware Ran OpenCode With 154 Models and Left Its Workspace Open: What SOCRadar FoundAn extortion crew called n0n used the open-source OpenCode coding agent to write and debug hundreds of attack scripts, then left its Python file server open to the internet. SOCRadar read the 1,719 files. Here is the attack chain, what is and is not confirmed, and what it means for anyone running coding agents.Page 4 of 21 · 245 posts