Mission

AI Browsers Have a Zero-Click Flaw: Protect Your Business Now

AI Browsers Have a Zero-Click Flaw: Protect Your Business Now

Know what attackers see before they do. See a live Radar report →

An employee gets a calendar invite. Nothing unusual about it, maybe a meeting from a vendor or a recruiter. Their AI browser, the one helping them triage email and summarize documents all day, reads the invite as part of its normal routine. Buried in the invite description is a line of text that looks like noise to a human and like an instruction to the AI. The browser follows it. No click. No download. No warning popup. By the time anyone notices, local files or login credentials are already gone.

That's not a hypothetical. It's PleaseFix, a set of vulnerabilities researchers at Zenity Labs demonstrated at Black Hat USA 2026 against three of the biggest names in agentic browsing at once.

One Flaw, Three Major Browsers, Zero Clicks

Zenity's research confirmed working attack chains against Claude in Chrome and ChatGPT Atlas through malicious text hidden in emails and social media posts, and against Perplexity Comet through a zero-click calendar invite that quietly exfiltrated local files. Related exposure has been flagged in Gemini in Chrome and Microsoft's Copilot Edge as well. These aren't competing products with isolated bugs. They're separate companies that all got hit by the same mechanism in the same month.

That's the part worth sitting with. We've written before about the risk of connecting Claude or any AI agent to Microsoft 365, where the danger was over-broad permissions a human granted on purpose. PleaseFix doesn't need permission at all. It arrives as content the agent was always going to read.

Why a Patch From One Vendor Doesn't Fix the Others

Here's the uncomfortable mechanics of it. The browsers didn't share code. They shared a training objective: the underlying language model is built to treat plausible-looking instruction text as a command, whether it comes from the person typing or from a calendar invite the agent happened to open. That's indirect prompt injection, and it means the vulnerability doesn't live in any one company's software. It lives in how the model decides what counts as an instruction in the first place.

A vendor can patch what their browser is allowed to fetch or act on. That narrows the door. It doesn't remove the underlying behavior, which is exactly why three different products from three different companies fell to variations of the same attack within weeks of each other. If you're waiting for "the patch" to make this go away, there isn't one single patch to wait for.

The Targets Are the Boring Stuff That Actually Matters

Zenity's confirmed impact classes are local file exfiltration and credential theft. Not a flashy ransomware payload, just quiet access to whatever files and logins the AI browser session already had open. That's the same quiet-access pattern we flagged in our piece on silent AI-driven downloads inside the browser: the attack doesn't need to look dramatic to do real damage. It just needs to go unnoticed.

For a small business, that means the employee running an AI browser isn't just at personal risk. If that session has access to a shared drive, a client portal, or saved company credentials, the blast radius extends to whatever that account can touch.

What To Actually Do About It This Week

  1. Find out who's running one. Claude in Chrome, ChatGPT Atlas, Perplexity Comet, Gemini in Chrome, Copilot Edge. Most small businesses have no idea which of these are already installed on employee machines.
  2. Cut the ones nobody's actually using for work. Convenience installs are pure downside once you know the attack doesn't require a click.
  3. Scope the sessions you keep. Don't run an AI browser from an account that can see every file and every login. Give it its own lane.
  4. Train on the new delivery methods. Phishing awareness has focused on links and attachments for years. Now a calendar invite or an X post can carry the same payload, straight into an agent that will act on it without asking.
  5. Treat vendor advisories as urgent, not routine. This is still an evolving patch cycle across multiple companies. When Anthropic, OpenAI, or Perplexity ship a fix, apply it the same day.

If any of this sounds familiar, it's the same discipline we recommend for any high-access tool: know what's connected, limit what it can reach, and verify instead of assuming. Our guide on the questions to ask before any AI tool touches your business data covers the same ground for tools your team adopts on purpose. PleaseFix is the reminder that some of the risk now arrives uninvited.

Take Action

AI browsers are going to keep showing up on employee machines whether IT approved them or not, and PleaseFix proves the risk isn't limited to permissions someone clicked "allow" on. The accounts, files, and credentials these tools can reach are exactly what a vulnerability scan is built to find before an attacker does. Oscar Six Security's Radar scan starts at just $99, with our BOGO2 bundle (3 scans for $99) available for teams covering more than one site. See our solutions and know what's actually exposed.

Focus Forward. We've Got Your Six.

Frequently Asked Questions

What is the PleaseFix vulnerability?

PleaseFix is a class of zero-click vulnerabilities in AI browsers, disclosed by Zenity Labs, where an attacker hides malicious instructions inside ordinary content like an email, a social media post, or a calendar invite. The AI agent reads that content during normal use and follows the hidden instructions automatically, with no click, download, or warning from the user.

Which AI browsers are affected by PleaseFix?

Zenity confirmed working exploit chains against Claude in Chrome, ChatGPT Atlas, and Perplexity Comet, with related findings extending to Gemini in Chrome and Microsoft's Copilot Edge. The attacks were demonstrated publicly at Black Hat USA 2026.

Why can't the vendors just patch this?

The root cause isn't a line of buggy code in any single browser. It's how the underlying AI models process text: they're trained to follow instruction-like language regardless of whether it came from the user or from content the agent happened to read. A code patch can narrow what the agent fetches, but as long as the model treats email bodies and calendar invites as potential instructions, the exposure stays open across every product built the same way.

What can a small business do about this right now?

Treat AI browser extensions like you'd treat any tool with broad account access: disable them for employees who don't need them, and for those who do, restrict what accounts and files the browser session can reach. Watch vendor security advisories for Claude in Chrome, ChatGPT Atlas, and Comet specifically, since patches are rolling out unevenly across products.

Does a vulnerability scan catch this kind of risk?

A scan won't find a prompt hidden in an email, but it will surface the exposed accounts, weak access controls, and unmonitored integrations that turn a successful AI browser hijack into a real breach. Oscar Six Security's Radar scan starts at $99 and is built for small businesses that need a clear picture of what's exposed.

Step-by-Step Guide

  1. Inventory who has an AI browser installed

    Check which employees have Claude in Chrome, ChatGPT Atlas, Perplexity Comet, Gemini in Chrome, or Copilot Edge enabled. Most IT teams don't know until they look.

  2. Turn it off where it isn't earning its keep

    If an employee installed an AI browser extension for convenience and isn't using it for real work, disable it. Fewer live agentic sessions means a smaller attack surface.

  3. Scope what the browser session can reach

    Where the tool is genuinely needed, limit the logged-in accounts and files available to that browser profile instead of running it from an account with access to everything.

  4. Flag calendar invites and external messages as a vector, not just email

    Train employees that a malicious instruction can now arrive through a calendar invite or a social post, not just a phishing email, since those are the confirmed PleaseFix delivery methods.

  5. Watch for vendor patches and apply them fast

    Anthropic, OpenAI, and Perplexity are patching unevenly. Subscribe to their security advisories and update browser extensions as soon as fixes land.

Find out what's exposed. Radar scans your external attack surface and shows you exactly what needs fixing. See a sample report →