Adversarial testing before deployment
The deployed agent is attacked in testing before it goes live.
Layer L3 Application · Owner Deployer · Family Testing, governance and output integrity
–Held
–Failed
–Got around
–Missing
By risk
| Risk | Held | Failed | Got around | Missing | Not mentioned |
|---|---|---|---|---|---|
| Agent takes destructive or unapproved actions | – | – | – | – | 3 |
| Agent escapes its sandbox | – | – | – | – | 5 |
| AI system attacked or breached | – | – | – | – | – |
| Physical harm | – | – | – | – | – |
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
No reported fix names this control yet.
Frameworks
| Framework | Item | Text |
|---|---|---|
| NIST SP 800-53 | CA-8 | To verify when the text is stored |
| EU AI Act | Art. 15 | To verify when the text is stored |