AI Risk Wire

Cases › security breach › LR-2026-0795

Chat agent socially engineered into revealing a long-lived OAuth token; CRM data of more than 700 companies reportedly at risk

Preliminary Why: Only a republished copy: BigGo Finance · subject to change

Developing: a major or severe case captured in the last 72 hours. Later changes are logged on the corrections page.

Status: no action reported

Severity major
Reported 23 Oct 2026

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

Severity major: Test applied: many third parties, a stated count of two or more affected parties. Fact: the token opened the door to more than 700 companies.

According to a press account of a talk by Bloomberg security practitioner Andrey Rybka, attackers social-engineered a chat agent into revealing a long-lived OAuth token. They then asked whether the agent could export CRM data, and it could. The token opened the door to more than 700 companies. The account is secondhand, names no organisation, gives no date, and does not say how the activity was detected or contained. The remedy it proposes is short-lived, audience-bound tokens, one identity per agent, tightly scoped, with an audit trail.

What happened

1 · What went wrongThe agent revealed a long-lived OAuth token.

What was done

No source states an action or fix.

Risks

AI used to run a cyber attack
Also
96 incidents
Rising: 24 vs 4.0 a week

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

Similar incidents

All cases of this kind ›

Evidence

No source states: what the AI was doing, what it reached or did, how it was caught, when it happened, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what was done.

Show the full account: 1 items from the primary sources

What happened, in order

Not dated in the sources:

  • Attackers social-engineered a chat agent into revealing a long-lived OAuth token, then asked whether it could export CRM data.
Show every field, with its source and grade

What happened

Earliest source we hold
2026-10-23
D inferred by us from the described behaviour, reason shown
What set it off
exposed credentials
C one secondary source states it
Who caused it
an outside attacker
C one secondary source states it
What went wrong
security breach
D inferred by us from the described behaviour, reason shown
AI agent
an AI agent acted
C one secondary source states it

Impact

Severity
major
D inferred by us from the described behaviour, reason shown
Why this severity
Test applied: many third parties, a stated count of two or more affected parties. Fact: the token opened the door to more than 700 companies.
D inferred by us from the described behaviour, reason shown

Notes on gaps

The source says the token opened access to more than 700 companies; the exact count is not recorded as an integer because the source states only a lower bound.

LR-2026-0795 · version 1 · published 2026-11-01 after automatic checks; not yet checked field by field by a person · JSON