Loading story…
Cloudflare has introduced Kitesurf, an experimental lightweight browser engine built for automated workflows and AI agents, designed to run browser components inside isolated WebAssembly and Rust environments on Cloudflare Workers. The platform supports the Chrome DevTools Protocol and is aimed at tasks such as page rendering, screenshot capture, and HTML extraction while using fewer resources than a full Chromium deployment.
Kitesurf draws on components from the Rust-based Blitz rendering engine and Firefox’s Stylo CSS parser, but Cloudflare says it is not yet a full replacement for Chromium. Current limitations include missing support for video, WebGL, realistic TLS-based bot challenges, and long-lived authenticated sessions. The announcement has also prompted discussion about Cloudflare’s position as both a provider of browser automation tooling and a vendor of anti-bot and cybersecurity services, while the company has said it plans to open source the project in the future.
Track how attackers are adapting to this technology.
1 event from the most recent confirmed update back to the earliest known activity.
Cloudflare introduced Kitesurf, an experimental lightweight browser engine for automated and AI-agent workloads running on Cloudflare Workers. The company said it supports the Chrome DevTools Protocol and is designed for tasks such as screenshots, HTML extraction, and page rendering with lower overhead than full Chromium.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Cloudflare has launched a developer preview that lets websites expose **WebMCP** interfaces through a single dashboard setting, extending Google Chrome’s emerging proposal for structured AI-agent access to web features. WebMCP is designed to let browser-based agents discover and invoke site-defined tools with **JSON Schema** inputs and outputs and shared page state, avoiding brittle HTML scraping and simulated clicks. Google has been testing the proposed standard in a Chrome origin trial beginning with Chrome 149, while Cloudflare said its preview currently works in Chrome 145 and later. Cloudflare’s implementation injects a `bridge.js` module into pages it serves, where tools can be registered statically or discovered dynamically and execution is proxied back to the site on the same origin. The preview includes two initial tool packs: **Content Credentials** for reading `C2PA` image provenance metadata and a **Site MCP Server** pack that exposes a site’s existing MCP server tools to in-browser agents. The rollout comes with security constraints already outlined in Chrome’s proposal, including requirements for origin-isolated documents, a `tools` Permissions Policy, and `allow="tools"` for cross-origin iframe use, while both the standard and Cloudflare’s implementation remain subject to change.
Aug 11, 2026
Cloudflare has open sourced **Cloudflare OS**, an internal platform built to control, isolate, and audit how AI agents access sensitive data and external tools. The system uses capability-based access controls and **Gatekeeper** services that hold credentials on an agent’s behalf, allowing policies to be enforced without exposing secrets directly to agent code. Cloudflare said the platform was designed to address security gaps in agent frameworks by limiting what agents can reach and by making their actions attributable and reviewable. A central feature is an observation log that records every resource an agent reads and uses that history to re-check whether downstream actions should still be allowed, extending beyond tool-permission models such as **Model Context Protocol**. Cloudflare said agent execution is isolated through **Dynamic Workers**, sandboxed browser frames, **Durable Object Facets**, and SQLite-backed application state, while model traffic is routed through **Cloudflare AI Gateway** for attribution, rate limiting, and budget controls. The company said Cloudflare OS is being released as open source before a broader managed product launch, with dashboard, development container, and Slack-integrated workspace features still in development.
Aug 23, 2026
Cloudflare has introduced **Precursor**, a client-side bot-detection system that identifies automated and agentic traffic by continuously analyzing behavior across an entire browsing session instead of relying on one-time challenges such as CAPTCHAs. Running in the browser through Cloudflare’s edge network, the system evaluates signals including mouse movement, scrolling patterns, typing cadence, clipboard use, page dwell time, and the consistency between pointer movement and page rendering to maintain an evolving bot-probability score. Cloudflare said Precursor preserves behavioral history across page reloads and can be enabled with one click without application code changes because the company automatically injects a lightweight script. The company also said the system does not capture the actual content users type, using aggregated timing and rhythm data instead, and positioned the launch as a response to increasingly sophisticated automated traffic that it estimates now represents about **57% of all web requests**.
Jul 21, 2026