| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MaliciousAgentSkills | SafeClaw-R | B9 | 13 | 2mo ago | |
| ClawHub | SkillVetBench | Overall Detection Rate95 | 9 | 1d ago | |
| ClawHub Unsafe File Ops 1.0 (n=10) | SkillVetBench | Catch Rate100 | 9 | 1d ago | |
| ClawHub Prompt Injection 1.0 (n=19) | SkillVetBench | Catch Rate100 | 9 | 1d ago | |
| ClawHub Command Injection 1.0 (n=27) | SkillVetBench | Catch Rate100 | 9 | 1d ago | |
| ClawHub Overall 1.0 | SkillVetBench | Overall Balance95 | 9 | 1d ago | |
| MaliciousAgentSkillsBench (404 malicious, 502 benign) | BIV | Recall100 | 9 | 21d ago | |
| MalSkillsBench | True Positives (TP)93 | 6 | 2mo ago | ||
| SkillFortifyBench (total) | SkillFortify | Precision100 | 1 | 3mo ago | |
| NPA Skills | - | - | 0 | 5d ago |