| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| LLM Agent Security | SkillJect 1.0 (test) | ASR5 | 8 | |
| Backdoor Injection | SkillJect 1.0 (test) | Attack Success Rate (ASR)100 | 8 | |
| Unauthorized Write | SkillJect 1.0 (test) | ASR98 | 8 | |
| Privilege Escalation | SkillJect 1.0 (test) | ASR98 | 8 | |
| Information Disclosure | SkillJect 1.0 (test) | ASR10,000 | 8 | |
| Efficiency Analysis | SkillJect | Tokens Used2,600 | 3 | |
| False Positive Evaluation | SkillJect (Benign) | Ori FP Rate0 | 3 | |
| Malicious Skill Detection | SkillJect (Malicious) | Originality98 | 3 |