| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Vulnerability Detection | SkillVetBench | Malicious Verdict Count0 | 9 | |
| Vulnerability Detection | SkillVetBench Privilege Abuse | Malicious Verdict Count0 | 9 | |
| Vulnerability Detection | SkillVetBench Supply Chain | Malicious Verdict Count0 | 9 | |
| Vulnerability Detection | SkillVetBench Data Exposure | Malicious Verdict Count0 | 9 | |
| Vulnerability Detection | SkillVetBench Unsafe File Ops | Malicious Verdict Count0 | 9 | |
| Vulnerability Detection | SkillVetBench Prompt Injection | Malicious Verdict Count0 | 9 | |
| Vulnerability Detection | SkillVetBench Command Injection | Malicious Verdict Count5 | 9 | |
| Vulnerability Detection | SkillVetBench Memory Poisoning | Malicious Verdict Count1 | 3 |