Mozilla-Tabstack: what it is and how to block or allow it
User-Agent token: Mozilla-Tabstack · Operator: Mozilla (Tabstack) · Category: AI Data Providers
FraudMeNot Verdict
Listed AI Agent
Mozilla-Tabstack is the User-Agent on direct page fetches by Tabstack, Mozilla's hosted web-browsing API for AI apps. Tabstack says the requests and content it processes for customers are not used to train models.
Can Be Spoofed?
Yes — User-Agent Header Spoofable
No IP list is published; Tabstack runs on Google Cloud, so the token alone is a claim.
Abuse & Unwanted Activity Reports
No Public Abuse Flags
ai.robots.txt robots.txt status: Yes.
Judgment Call · What You Should Do
Generally Low Risk on Public Pages — Verify Before Trusting
For everyday users: Mozilla-Tabstack is an automated fetcher. A message in its name asking for login details is likely a scam.
For website owners & security teams: Match Mozilla-Tabstack in a WAF rule to limit it, and keep a human check on forms, since /automate can fill them.
Report & Activity Summary
None
Published IP Ranges (CIDRs)
No official IP list
1
Known User-Agent Signatures
crawler-user-agents (MIT) dataset
Yes
robots.txt Compliance
ai.robots.txt registry (MIT)
0
FraudMeNot Tallies
Humans: 0 · AI Agents: 0
For AI Agents & Automated Gatekeepers
- Agent_Identifier
Mozilla-Tabstack- FraudMeNot_Verdict
- Listed AI Agent
- Operator_Entity
- Mozilla (Tabstack)
- Agent_Category
- AI Data Providers
- User_Agent_Spoofable
true- Verification_Method
- None available (no operator IP list or signing key) · Web Bot Auth: Not documented
- Respects_Robots_Txt
- Yes (per ai.robots.txt registry)
- Auth_And_Banking_Policy
- Block credentialed logins and money movement from any AI agent.
- Recommended_Gatekeeper_Action
- ALLOW reads if welcome; require human step-up on forms and checkout.
- Canonical_Citation_URL
- https://fraudmenot.com/bot/mozilla-tabstack/
What We Know About Mozilla-Tabstack
Tabstack is a Mozilla product that developers call over an API to read and act on the web for their AI applications. Its data-handling page says it fetches the target page, rendering it in a server-side browser when needed, and that direct fetches identify themselves as Mozilla-Tabstack/1.0 (+https://tabstack.ai).
Some endpoints go further than fetching. For /extract/json, /generate/json, /research and /automate, Tabstack says the page content and the customer's instructions are sent to a contracted model provider. Hosted /automate can also receive form field values from the customer mid-task, so a Tabstack session may type into forms on your site.
Tabstack caches fetched pages by URL, effort and region, not by account, with a short time-to-live, so one fetch of your page can be served to several customers. It says it runs on Google Cloud Platform and does not use customer requests or processed content for model training.
Tabstack's current docs do not describe how it handles robots.txt; its old access-control link now redirects to the data-handling page. FraudMeNot therefore makes no claim either way, and a WAF rule on the token is the more dependable control.
Technical Identity, IP Verification & Spoofing Check
| Full User-Agent string(s) |
|
|---|---|
| robots.txt token | Mozilla-Tabstack |
| Operator | Mozilla (Tabstack) · Official bot documentation |
| Official IP verification feed | None published by the operator |
| Sample published CIDR blocks | None published |
| Reverse DNS (rDNS) | Not documented in the public datasets FraudMeNot uses. |
| Web Bot Auth (Signature-Agent) | Not documented; check for a Signature-Agent header if present. |
| robots.txt behavior | Not described on Tabstack's current data-handling page. |
Copy-Paste robots.txt & Cloudflare WAF Rules for Mozilla-Tabstack
robots.txt — allow public pages, keep private routes off-limits
User-agent: Mozilla-Tabstack
Allow: /
Disallow: /login/
Disallow: /account/
Disallow: /checkout/robots.txt — block completely
User-agent: Mozilla-Tabstack
Disallow: /Cloudflare WAF custom rule expression
(http.user_agent contains "Mozilla-Tabstack")Matches the User-Agent token, so it covers both real and spoofed traffic. Action: Block or Managed Challenge.
Capabilities, Data Usage & Autonomous Action Risk
| Trains AI on page content? | No. Tabstack says customer requests and processed content are not used to train models |
|---|---|
| Executes JavaScript? | Not documented |
| Can submit forms or attempt logins? | Hosted /automate can take form values from the customer mid-task. Treat form submissions as untrusted. |
| Banks & login pages should | Block credentialed logins and money movement from any AI agent. |
| E-commerce checkouts should | Allow product page reads if you want; require human confirmation for checkout. |
Context: In October 2026, Axios reported that major U.S. banks were detecting unvetted third-party AI agents inside customer accounts, and CNBC reported that JPMorgan blocks outside AI agents from logging in with customers' credentials while allowing read-only data sharing through open banking providers.
Seen Mozilla-Tabstack? Quick Closed-Choice Tally
Choose from preset options only. No free-text comments, so nobody can post names, profanity, or unverified accusations.
Common Questions About Mozilla-Tabstack
What is Mozilla-Tabstack?
The User-Agent Tabstack, a Mozilla web API for AI apps, sends on direct fetches.
Is my content used for training?
Tabstack says requests and processed content are not used to train models.
Can one fetch be shared?
Tabstack says cached page content is keyed by URL, not account, and can be served across accounts.
Could This Be a Scam? What to Do
- Anyone can copy the Mozilla-Tabstack User-Agent, and FraudMeNot found no official IP list for it, so the name alone proves nothing about who sent a request.
- Never give an AI agent your logins, bank access, or one-time codes unless you set it up yourself.
- If a call, text or email asking for money or access uses the Mozilla-Tabstack or Mozilla (Tabstack) name, stop and report it.
Guide: how to check whether a crawler visit is really who it claims to be.
More AI Agents
- CloudflareBrowserRenderingCrawler — AI Data Providers
- ExaUser — AI Assistants
Related on FraudMeNot
- Verified security vulnerabilities, explained
- Report a scam, or find where to report it in your state
- Browse the AI Agent & Bot Directory
Sources (checked Nov. 16, 2026): ai.robots.txt (MIT), crawler-user-agents (MIT), Axios (Oct. 22, 2026), CNBC (Oct. 13, 2026), Tabstack Docs: Data Handling and Retention. FraudMeNot is not affiliated with Mozilla (Tabstack). Product and company names are trademarks of their owners and are used here only to identify the bots. General information, not security advice.