Physical harm
A robot, vehicle or device driven by AI causes physical harm.
NIST AI 600-1 · No exact NIST AI 600-1 categoryNIST AI RMF (safe)
2incidents (primary) · 0 more as secondary
0read for controls · 2 not yet
0fixes reported
0repeats after a fix
Incidents per quarter
2025-Q3: 0 · 2025-Q4: 1 · 2026-Q1: 0 · 2026-Q2: 0 · 2026-Q3: 0 · 2026-Q4: 1
Developers
Waymo · 1
Where the chain broke
| Layer | Held | Did not hold | Not mentioned | Attacker's own | Not read yet |
|---|---|---|---|---|---|
| L1 Model Model provider | – | – | – | – | 2 |
| L2 Harness Agent framework vendor | – | – | – | – | 2 |
| L3 Application Deployer | – | – | – | – | 2 |
| L4 Infrastructure / target Organisation hit | – | – | – | – | 2 |
Controls for this risk, by layer
HeldFailedGot aroundMissing
| Control | Held | Failed | Got around | Missing | Not mentioned | Did not hold, last 6 quarters | Added in fixes | Most common reason |
|---|---|---|---|---|---|---|---|---|
| Stop control L2 Harness | – | – | – | – | – | – | ||
| Human approval for high-impact actions L3 Application | – | – | – | – | – | – | ||
| Live behaviour monitoring L3 Application | – | – | – | – | – | – | ||
| Adversarial testing before deployment L3 Application | – | – | – | – | – | – | ||
| Physical safety interlocks L3 Application | – | – | – | – | – | – |
5 of 5 controls for this risk not yet seen holding.
Fixes reported and what followed
No remediation reported for incidents of this risk.
Incidents
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Chain | Controls named |
|---|---|---|---|---|
| 2026-10-23 | Garage-built ChatGPT-controlled smart rifle fires on voice command; OpenAI revokes engineer's access | Physical harm | Not read yet | |
| 2025-10-27 | Waymo robotaxi strikes and kills cat KitKat in San Francisco Waymo |
Physical harm | Not read yet |