Vulnerability scanning of AI components
Agent platforms and their services are scanned and patched.
Layer L3 Application · Owner Deployer · Family Supply chain
–Held
–Failed
–Got around
–Missing
By risk
| Risk | Held | Failed | Got around | Missing | Not mentioned |
|---|---|---|---|---|---|
| Agent escapes its sandbox | – | – | – | – | 5 |
| Supply-chain compromise | – | – | – | – | 1 |
| AI system attacked or breached | – | – | – | – | – |
Why it did not hold
No incident yet records this control not holding.
By quarter
| Period | Held | Failed | Got around | Missing |
|---|---|---|---|---|
| 2025-Q3 | – | – | – | – |
| 2025-Q4 | – | – | – | – |
| 2026-Q1 | – | – | – | – |
| 2026-Q2 | – | – | – | – |
| 2026-Q3 | – | – | – | – |
| 2026-Q4 | – | – | – | – |
Added in reported fixes, and what followed
| Incident | Developer | Date | Later incidents where it did not hold |
|---|---|---|---|
| LR-2026-0265 Unreleased Anthropic research model chains zero-days into working exploits across Chrome, Safari, Android, Windows and Linux | Anthropic | 2026-10-28 | None on record |
| LR-2026-0188 Waymo robotaxi maneuvers around stopped, unloading school bus in Atlanta | Waymo | 2026-10-15 | None on record |
| LR-2026-0137 Meta Muse AI agent KVM escape vulnerability discovered before launch | Meta | 2026-10-08 | None on record |
| LR-2026-0123 Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure | 2026-10-04 | None on record | |
| LR-2026-0090 AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent | OpenAI | 2026-07-23 | None on record |
Frameworks
| Framework | Item | Text |
|---|---|---|
| MITRE ATLAS | AML.M0016 | To verify when the text is stored |
| NIST SP 800-53 | RA-5 | To verify when the text is stored |