| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Malicious Skill Detection | ClawHub | Overall Detection Rate95 | 9 | |
| Malicious Skill Detection | ClawHub Unsafe File Ops 1.0 (n=10) | Catch Rate100 | 9 | |
| Malicious Skill Detection | ClawHub Prompt Injection 1.0 (n=19) | Catch Rate100 | 9 | |
| Malicious Skill Detection | ClawHub Command Injection 1.0 (n=27) | Catch Rate100 | 9 | |
| Malicious Skill Detection | ClawHub Overall 1.0 | Overall Balance95 | 9 | |
| Discovery Manipulation | ClawHub | Top-3 Accuracy56 | 5 | |
| Discovery Manipulation | ClawHub 0-day | Win-Rate94 | 2 | |
| Discovery Manipulation | ClawHub average-day | Win-Rate74.14 | 1 |