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 26 of 38
451 posts
Oct 25, 2026 · 11 min readBackdoored Open-Weight Qwen Model Steals .env Files Through CodexProjectDiscovery showed that an edited open-weight model can pass normal checks and still run a credential-stealing command when a chosen phrase appears. Here is how the backdoor works, what is and is not proven, and what to lock down if you point a coding agent at a model you did not train.
Oct 25, 2026 · 10 min readMalicious AGENTS.md in Downloads: How a Planted File Hijacks Codex and Claude CodeForever Security found a malicious AGENTS.md in a customer's Downloads folder that steered a coding agent toward a known-bad npm package. Nothing is patchable: the agent did what instruction files are for. Here is the chain, who is exposed, and what to change today.
Oct 24, 2026 · 7 min readBrotli CVE-2026-111497: Affected Software, Detection and Fixes Beyond Node.jsThe Brotli decoder bug behind CVE-2026-111497 was fixed upstream on February 27, 2026 and only recognized as a security flaw in October. This guide lists every fixed release we could verify, how each ecosystem reaches the decoder, how to detect exposure, and what to do for AI agents that fetch untrusted URLs.
Oct 24, 2026 · 8 min readThe "Universal Jailbreak" Claim: Spoofed Tool Calls, CTF Framing and What Is VerifiedAn X post claims a "universal jailbreak" that spoofs tool calls so models trust fake CTF links, emails and locations. The technique class is real and documented; the universal claim has no public evidence yet. Here is the split, and what it means for people running coding agents.
Oct 24, 2026 · 6 min readTypeSafe AI's "Customer Output Leak" Was a Joke. October 2026's Attacks Are NotOn October 23, TypeSafe AI CEO Diogo Almeida announced a "massive unauthorized leak of ALL customer outputs" and linked a gist. It held the numbers 0.00 through 1.00 and nothing else. The joke worked because the real incident feed is so noisy right now. Here is how to tell a joke from a breach, and what to do about the real ones.
Oct 24, 2026 · 11 min readWhat to Do After an Attack on Your App: An Incident Response Playbook by Attack TypeAn alert says your app was attacked. This is the playbook: what to do in the first 15 minutes, how to decide whether it is real, and step-by-step responses for injection, AI feature attacks, server compromise, leaked credentials, reconnaissance and vulnerable dependencies.
Oct 23, 2026 · 10 min readAPI Keys in Logs and Env Vars: How They Leak and How to Catch It EarlyEnvironment variables hold the keys attackers want, and logs are where those keys quietly spread. This guide covers the common leak paths, a rotation checklist ordered by blast radius, and how beam monitor can flag credentials written to logs.
Oct 23, 2026 · 11 min readApp Monitoring in a Platform Breach: What It Can and Cannot CatchOpenCode and Railway were breached upstream of their customers. App monitoring would not have stopped either one. This post is about what you still control when the compromise happens on someone else's servers, and where log-based monitoring genuinely helps.
Oct 23, 2026 · 10 min readCheck Dependencies Against Known CVEs in CI with beam cve checkbeam cve check reads your lockfiles, sends only package names and versions, and matches them against AgentBeam's CVE database. This guide shows how to run it locally, gate a CI build with --fail-on, and read the results.
Oct 23, 2026 · 15 min readYour First 24 Hours After a Vendor Breach: A Rotation and App Monitoring RunbookWhen a platform, tool or dependency you use discloses a compromise, the first day decides how much it costs you. This hour-by-hour runbook covers mapping exposure, rotating by blast radius, hunting in logs, and hardening afterwards, with what app monitoring can and cannot tell you.
Oct 23, 2026 · 10 min readLet Your Coding Agent Set Up AgentBeam: The agentbeam-setup and agentbeam-app-monitoring SkillsAgentBeam ships two skills your coding agent can follow to set things up for you: agentbeam-setup and agentbeam-app-monitoring. One npx command installs them for every agent, and Beam scans each skill before it installs.
Oct 23, 2026 · 14 min readMonitor an App Hosted on Railway (or Any PaaS) for Attacks: Set Up beam monitor in MinutesWhen your app runs on a PaaS such as Railway, you see only what the platform shows you. This guide sets up beam monitor as a separate service next to the app, so the app stays untouched, then covers the token, the monitoring level, a Slack webhook, beam monitor test and status, first-week tuning, and what to do the day your host discloses a breach.Page 26 of 38 · 451 posts