Agent Action
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Indirect Prompt Injection | Agent Action Subset 2 | IR0 | 24 | |
| Agent Action | Agent Action subset | RR98 | 12 | |
| Prompt Injection Attack Success | Agent Action | IR85 | 10 | |
| Indirect Prompt Injection Attack Success Evaluation | Agent Action Goal-Distant 2 | IRany88 | 5 | |
| Indirect Prompt Injection Attack Success Evaluation | Agent Action Goal-Adjacent 2 | IRany85 | 5 |
Showing 5 of 5 rows