AI coding agents hijacked using AGENTS.md file in Downloads folder
Researchers 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. [...]
$ webdevs --week 2026-43
19 Oct – 25 Oct 2026. 60 links on AI, security, web development, and design.
$ cat notes/2026-43.md
A heavy security week. Two critical PHP flaws, later named PHP2Shell, were disclosed on 21 October; Cloudflare had WAF rules in place before the announcement, and Krebs on Security warned the flaw could cause many site outages. The same week brought a pre-authentication command execution flaw in NetScaler Gateway (CVE-2026-88771), eight eMudhra intermediate certificates found to use weak keys, and the BlackX UEFI bootkit bypassing Secure Boot. Coding agents got their own warning: researchers found a malicious AGENTS.md file in a Downloads folder that tricked an agent into installing a rogue npm package.
On the tooling side, Cloudflare is collaborating on tsrs, a Rust port of TypeScript that it says is up to 8x faster and uses 70% less memory. The exploitation of PHP2Shell, and a second critical bug in Brotli, follow on the week 44 page.
Researchers 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. [...]
AI firms keep hiring human designers. Ironic much?
Learn how OpenAI scaled Habitat with reliable multi-tenancy, global caching, and Azure Cosmos DB to deliver 12× faster reads for ChatGPT.
OpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.
Anima expands what care teams can do with OpenAI models, giving them more capacity to respond to patients.
Fast, focused, low-cost decisions for any application.
What forward deployed engineering means at OpenAI
Uber is rolling out ChatGPT Work to more than 30,000 employees, helping teams research, analyze data, create presentations, and complete complex workflows.
How OpenAI works with distribution partners to uphold consistent safeguards, support responsible access, and clarify expectations in our Usage Policies.
AT&T is working with OpenAI to make legal knowledge easier to access. Learn how its LegalEdge team is rethinking intake and scaling legal judgment.
We moved a copy of 99.99999% of GitHub's repositories to Azure. Here's how per-reference quorums will bring over the rest, and how object storage lets reads scale…
Almost 100,000 Commerce.com domains now give AI agents real shopping tools through WebMCP on Cloudflare. Here's how we turned it on across every store at once, while…
From local businesses to global brands, more advertisers can now reach people as they explore, compare and decide what to buy in ChatGPT.
OpenAI and Google Cloud are bringing frontier models and Codex workflows to Gemini’s Model Garden, available through Google Cloud Marketplace.
Learn how OpenAI built ChatGPT’s LLM-powered ad stack to understand conversational intent, keep ads separate from answers, and deliver relevant ads at scale.
See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.
Three Java Champions share how they use GitHub Copilot to solve problems, accelerate development, and keep humans responsible for the results. The post How 3 Java…
An independent Schlotzsky’s and Cinnabon franchisee cut menu repricing time by 95% and built a workflow that could free up $100K in cash flow.
Terminal X’s Eval Agent grades outputs against a 54-criterion rubric, catching 25% more deviances from a fund’s mandate with GPT-6.1 Sol.
When our AI code reviewer's cost per run doubled, we dug into the token usage to find out why. Learn how we used prompt caching and intelligent model routing to slash…
Learn how to move an agent session from the GitHub Copilot app into VS Code without losing the conversation, code changes, or working context. The post How to continue a…
Clairic is a new model from Cloudflare that is a System One extraction modeI, capable of extracting, computing, estimating, and forecasting data from unstructured inputs.
A new UEFI bootkit named BlackX, deployed in an espionage campaign in early 2026, exploited the old Baton Drop vulnerability to bypass Secure Boot and load a malicious…
Turning on Personal Intelligence gives the company more data for ad targeting.
Cloudflare's new post-quantum GeoKey Manager protects geographically fenced decryption keys from harvest now, decrypt later attacks. Learn how we redesigned our…
OpenAI and Poland’s NASK are partnering on AI safety, security, and technical research to strengthen safeguards and support a more resilient digital ecosystem.
As Cybersecurity Awareness Month continues, the GitHub Bug Bounty team spotlights @r31n, diving into their research approach, favorite bug classes, and advice for…
Expect to see quite a few websites serving "404" or "Page Not Found" errors today: Nearly 70 percent of websites need to update their core software to fix a pair of…
Cloudflare's web application firewall can now correlate an HTTP request with its response. Full transaction detection helps every customer find successful exploits, data…
Cloudflare has deployed default web application firewall (WAF) protections for newly disclosed PHP vulnerabilities before public disclosure. The rules use request and…
Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities across open source.
Cloudflare uses OpenAI Daybreak to investigate vulnerabilities and propose fixes for review. Its developers use Codex to build faster and improve code quality.
OpenAI outlines a blueprint for empowering cyber defenders with frontier AI, stronger safeguards, modernized cybersecurity, and more resilient public institutions.
U.S. federal investigators pursuing the ShinyHunters hacking group that recently stole highly sensitive data from the FBI have identified executives at two different…
CVE-2026-88771 lets attackers run commands on NetScaler Gateway before anyone signs in. Patching takes time most teams don't have, so the sign-in decision has to move in…
Naive byte-range caching can waste gigabytes of origin bandwidth on small requests. We rebuilt our cache architecture in Pingora to coordinate partial fetches…
Cloudflare has achieved South Korea's ISMS certification following an audit across 80 controls. Learn how we localized user consent flows, adapted social sign-up paths…
Following the discovery that eight eMudhra intermediate certificates use weak keys, Cloudflare is deploying mitigations and releasing client updates. We explain the…
Cloudflare is collaborating on tsrs, a Rust port of TypeScript that is up to 8x faster and uses 70% less memory.
(And this time even harder).
We caught up with the brand's Chief Marketing Officer to find out how Ben & Jerry's puts its values into practice.
From minimalist silk prints to hand-painted masterpieces, these are to die for.
Colour is now banned?
The creative director makes the case for backing yourself in his new book, Daring Forever.
A closer look at accordion icons, why split menus are harmful, and why it’s better not to have icons and text labels link to different actions. Plus, why the caret is…
Design systems thrive on consistency, so where does randomness fit in? Through playful demos of organic typography, bouncing letters, and splayed cards, Brecht De Ruyte…