LLM Agent Security Evaluation on AgentDojo vulnerable-agent profile stress test (six banking pairs)
0Attack Success Count (out of 6)
Deny
Updated 2mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 0 | 2 | 6 | 0 | |
2026.05 | 0 | 4 | 31 | 0 | |
2026.05 | 0 | 4 | 4 | 4 | |
2026.05 | 6 | 2 | 0 | 0 | |
2026.05 | 6 | 2 | 0 | 0 |