Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578)
An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.
| Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
|---|---|---|---|---|
| Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) | MITRE ATLAS Attack Pattern | LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) | MITRE ATLAS Attack Pattern | 1 |