Explains system security risks
Abuse of excessive or legitimate privilege, unauthorised privilege elevation, service account abuse, platform intrusion, SQL injection, default passwords, backup data abuse.
Can AI do this?
Not settled yet The benchmark tested this, but the models' answers do not settle yet whether they master it. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 71% | Not shown |
| gemini-3.5-flash-lite | Low cost | 63% | Not shown |
| gpt-6-luna | Low cost | 70% | Not shown |
| claude-haiku-5-5 | Low cost | 69% | Not shown |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: Abuse of excessive or legitimate privilege, unauthorised privilege elevation, service account abuse, platform intrusion, SQL injection, default passwords, backup data abuse.
How it is assessed: Answers a CDMP-style multiple-choice question on the system security risks
All knobits of Data security.
Source: DAMA-DMBOK: Data Management Body of Knowledge, 2nd edition (revised), chapter 7: Data Security, element SV-16