AI system attacked or breached

The AI product or its infrastructure is the target of the attack.

NIST AI 600-1 · Information SecurityMITRE ATLAS

1incidents (primary) · 73 more as secondary

0read for controls · 1 not yet

0fixes reported

0repeats after a fix

Incidents per quarter

2025-Q3: 0 · 2025-Q4: 0 · 2026-Q1: 0 · 2026-Q2: 0 · 2026-Q3: 0 · 2026-Q4: 1

Meta · 1

Layer	Held	Did not hold	Not mentioned	Attacker's own	Not read yet
L1 Model Model provider	–	–	–	–	1
L2 Harness Agent framework vendor	–	–	–	–	1
L3 Application Deployer	–	–	–	–	1
L4 Infrastructure / target Organisation hit	–	–	–	–	1

HeldFailedGot aroundMissing

Control	Held	Failed	Got around	Missing	Not mentioned	Added in fixes
Short-lived, scoped credentials L3 Application	–	–	–	–	–	–
Segmentation of agent components L3 Application	–	–	–	–	–	–
Live behaviour monitoring L3 Application	–	–	–	–	–	–
AI incident response plan L3 Application	–	–	–	–	–	–
Vulnerability scanning of AI components L3 Application	–	–	–	–	–	–
Encryption of stored data L3 Application	–	–	–	–	–	–
Adversarial testing before deployment L3 Application	–	–	–	–	–	–
Known flaws patched L4 Infrastructure / target	–	–	–	–	–	–
Intrusion and endpoint detection L4 Infrastructure / target	–	–	–	–	–	–
Inventory of exposed services L4 Infrastructure / target	–	–	–	–	–	–

10 of 10 controls for this risk not yet seen holding.

No remediation reported for incidents of this risk.

HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target

Date	Incident	Risk	Chain	Controls named
2026-10-25	Unauthorized third-party AI agents detected operating inside US bank customer accounts Meta	AI system attacked or breached		Not read yet