Cases › security breach › LR-2026-0287
Accenture contractor's Claude Code agent leaked NIPRNet credentials and network map to third-party website
Preliminary Why: Publisher not yet named · subject to change
Developing: a major or severe case captured in the last 72 hours. Later changes are logged on the corrections page.
Severity major: A live production compromise of a secure DoD network used by multiple intelligence agencies, with credentials leaked to a third-party site and other controlled unclassified information potentially at risk.
Earliest source we hold 2026-10-30 · Captured by AI Risk Wire 2026-10-31 02:29 UTC
An Accenture contractor gave a personal Claude Code agent login credentials to the DoD's NIPRNet secure production environment to write and deploy code.
Risks this incident falls under
| Risk | Role | NIST AI 600-1 | Incidents | Last 6 quarters |
|---|---|---|---|---|
| Data leaked or sent out | Primary | Data Privacy | 3 | |
| AI used to run a cyber attack | Also | Information Security | 33 | |
| AI system attacked or breached | Also | Information Security | 1 |
Sorted by rule from the case's fields; not yet read from the sources.
Control failure chain
L1 · ModelProvider not namedModel provider
Sources not yet read for controls.
Model version not linked to a model card.
L2 · HarnessHarness not namedAgent framework vendor
Sources not yet read for controls.
1 more for this risk at this layer
L3 · ApplicationDeployer not namedDeployer
Sources not yet read for controls.
6 more for this risk at this layer
L4 · Infrastructure / targetOrganisation hitOrganisation hit
Sources not yet read for controls.
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
The same controls in other incidents of this risk
| Control | Layer | Here | Held elsewhere | Did not hold elsewhere |
|---|---|---|---|---|
| Network egress control | L2 Harness | Not read yet | – | – |
| Least-privilege access for the agent | L3 Application | Not read yet | – | – |
| Human approval for high-impact actions | L3 Application | Not read yet | – | – |
| Output filtering and redaction | L3 Application | Not read yet | – | – |
| Activity logs | L3 Application | Not read yet | – | – |
| Data minimisation | L3 Application | Not read yet | – | – |
| Sensitive-data checks on outbound data | L3 Application | Not read yet | – | – |
Remediation
Fix reported
“The risk was identified and patched”
Vulnerability scanning of AI components
No later incident for Anthropic under this risk on record.
Risk grouping: Not yet classified
No source we hold states: who caused it, intended or not, before or after release, the ai's part.
The story
What the sources state
- Cause a permission, scope or wiring error
No source states: 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, what set it off.
Others like this
CyberXero AI-augmented initial access campaign using Claude Code and PentAGI agents 2026-10-12
Anthropic Claude model develops working Linux kernel MPTCP root exploit (CVE-2026-98432) 2026-10-30
Show every field, with its source and grade
The AI system
What happened
Impact
Context
LR-2026-0287 · version 2 · published 2026-10-31 after automatic checks; not yet checked field by field by a person · changes to this case · JSON