AI Risk Wire

Cases › security breach › LR-2026-0826

WorkOS internal sales application breached via AI-assisted offensive framework ARTEX

Confirmed Why: 2 independent outlets · 2 independent reports

Status: fix reported

Severity moderate
Reported 2 Nov 2026
Agent tool ARTEX
Industry Software / identity and authentication services

No source states: loss or records, developer and model, could do, deployer.

Severity moderate: Data of third parties (WorkOS customers) was touched with a bounded scope stated: contact details, account histories and conversation excerpts in an internal sales application, with no confirmed record-by-record account of what was accessed.

WorkOS confirmed unauthorized access to an internal sales application holding customer contact information, account histories and excerpts from sales calls, support discussions and customer Slack conversations. The company detected the incident on October 30, 2026, and published a security bulletin on November 2. Its investigation identified an AI-assisted offensive security framework used to automate reconnaissance and exploitation attempts; CEO Michael Grinich named the tool as ARTEX, an AI-powered framework that automates offensive security tasks. WorkOS said there is no evidence that WorkOS application data or production services were accessed or impacted, and that the investigation currently points to CRM and customer support information. WorkOS disabled external access to the affected application, began reviewing access controls across internal tools, and retained an independent digital forensics and incident response firm.

What happened

No source tells the story step by step yet.

What was done

Fix reported

“WorkOS disabled external access to the affected application, began reviewing access controls across internal tools, and retained an independent digital forensics and incident response firm.”

Risks

Credential and privilege abuse
Primary46 incidents
AI used to run a cyber attack
Also89 incidents
Rising: 25 vs 4.0 a week
AI system attacked or breached
Also20 incidents

Sorted by rule from the case's fields; not yet read from the sources.

Controls

Not yet read for controls. Controls that mitigate the primary risk:

Application

Short-lived, scoped credentials · Secrets kept out of the model's context · Separate identity for each agent · Least-privilege access for the agent · Alerts on unusual tool use · Activity logs · Sensitive-data checks on outbound data

Infrastructure / target

Multi-factor sign-in and password policy · Secrets scanning

Evidence

No source states: a step-by-step account, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off.

Show every field, with its source and grade

The AI system

Software around the model
ARTEX
C one secondary source states it
How much it acted alone
it acted alone, watched by a person
C one secondary source states it
What it was for
automates offensive security tasks
C one secondary source states it

What happened

When it happened
2026-10-30
C one secondary source states it
Earliest source we hold
2026-11-02
C one secondary source states it
Themes
AI assisted cyberattack, agentic AI, multi-agent, data breach, credential theft, cyberattack
C one secondary source states it
Who was responsible
an outside party
C one secondary source states it
Who caused it
an outside attacker
C one secondary source states it
What was done
WorkOS disabled external access to the affected application, began reviewing access controls across internal tools, and retained an independent digital forensics and incident response firm.
C one secondary source states it
What went wrong
security breach
C one secondary source states it
AI agent
an AI agent acted
C one secondary source states it
What it did
The source states that ARTEX agents automate reconnaissance and exploitation and that stolen application credentials can support attacks across customer environments.
C one secondary source states it

Impact

Severity
moderate
C one secondary source states it
Kind of harm
privacy, others' security
C one secondary source states it
Who was affected
names, email addresses, phone numbers, job titles, and company affiliations stored in customer relationship management systems
C one secondary source states it
Kinds of data exposed
personal information
C one secondary source states it
Why this severity
Data of third parties (WorkOS customers) was touched with a bounded scope stated: contact details, account histories and conversation excerpts in an internal sales application, with no confirmed record-by-record account of what was accessed.
C one secondary source states it

Context

Industry
Software / identity and authentication services
C one secondary source states it
Investigated
by a paid outside firm
C one secondary source states it

Notes on gaps

The document explicitly says the ARTEX reports do not establish attribution for WorkOS, so the link between ARTEX and this breach rests on the CEO's statement. Extractor proposed values without quotes; dropped: . The document does not name the AI framework, model, or threat actor, nor the initial access mechanism, vulnerability, or credentials involved. Extractor proposed values without quotes; dropped: .

LR-2026-0826 · version 1 · published 2026-11-04 after automatic checks; not yet checked field by field by a person · JSON