Active Directory domain escalation on GOAD 5 hosts
80Domain Escalation Success RatePENTESTGPT V2
Evaluation Results
| Method | Links | |
|---|---|---|
| PENTESTGPT V2Model=GPT-5.2, Thinking Mode=Thinking2026.02 | 80 | |
| PENTESTGPT V2Model=Opus 4.5, Thinking Mode=Thinking2026.02 | 80 | |
| PENTESTGPT V2Model=GPT-5.2, Thinking Mode=Standard2026.02 | 60 | |
| PENTESTGPT V2Model=Opus 4.5, Thinking Mode=Standard2026.02 | 60 | |
| PENTESTGPT V2Model=Gemini 3, Thinking Mode=Standard2026.02 | 60 | |
| PENTESTGPT V2Model=Gemini 3, Thinking Mode=Thinking2026.02 | 60 | |
| PentestGPTModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 40 | |
| PentestAgentModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 40 | |
| PentestAgentModel=Opus 4.5, Thinking Mode=Standard2026.02 | 40 | |
| PentestAgentModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 40 | |
| VulnBotModel=GPT-5.2, Thinking Mode=Standard2026.02 | 40 | |
| VulnBotModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 40 | |
| VulnBotModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 40 | |
| VulnBotModel=Gemini 3, Thinking Mode=Thinking2026.02 | 40 | |
| PentestGPTModel=GPT-5.2, Thinking Mode=Standard2026.02 | 20 | |
| PentestGPTModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 20 | |
| PentestGPTModel=Opus 4.5, Thinking Mode=Standard2026.02 | 20 | |
| PentestGPTModel=Gemini 3, Thinking Mode=Standard2026.02 | 20 | |
| PentestGPTModel=Gemini 3, Thinking Mode=Thinking2026.02 | 20 | |
| AutoPTModel=GPT-5.2, Thinking Mode=Standard2026.02 | 20 | |
| AutoPTModel=GPT-5.2, Thinking Mode=Thinking2026.02 | 20 | |
| AutoPTModel=Opus 4.5, Thinking Mode=Thinking2026.02 | 20 | |
| AutoPTModel=Gemini 3, Thinking Mode=Standard2026.02 | 20 | |
| AutoPTModel=Gemini 3, Thinking Mode=Thinking2026.02 | 20 | |
| PentestAgentModel=GPT-5.2, Thinking Mode=Standard2026.02 | 20 | |
| PentestAgentModel=Gemini 3, Thinking Mode=Standard2026.02 | 20 | |
| PentestAgentModel=Gemini 3, Thinking Mode=Thinking2026.02 | 20 | |
| VulnBotModel=Opus 4.5, Thinking Mode=Standard2026.02 | 20 | |
| VulnBotModel=Gemini 3, Thinking Mode=Standard2026.02 | 20 | |
| AutoPTModel=Opus 4.5, Thinking Mode=Standard2026.02 | 0 |