List your company

Prompt Injection Attack on AgentDojo

64ASR@1PISmith
-2.5614.723249.28Mar 13, 2026

Evaluation results

MethodLinks
PISmithTarget Model=GPT-4.1-nano2026.036481—
PISmithTarget Model=GPT-4o-mini2026.036278—
PISmithTarget Model=GPT-5-nano2026.032438—
Imp. Instr.Target Model=GPT-4o-mini2026.0323——
Tool Know.Target Model=GPT-4.1-nano2026.0320——
Imp. Instr.Target Model=GPT-4.1-nano2026.0320——
Ignore Prev.Target Model=GPT-4.1-nano2026.0313——
Tool Know.Target Model=GPT-4o-mini2026.0312——
Ignore Prev.Target Model=GPT-4o-mini2026.036——
InjecagentTarget Model=GPT-4.1-nano2026.035——
InjecagentTarget Model=GPT-4o-mini2026.034——
DirectTarget Model=GPT-4.1-nano2026.034——
Sys. MsgTarget Model=GPT-4.1-nano2026.034——
DirectTarget Model=GPT-4o-mini2026.033——
Sys. MsgTarget Model=GPT-4o-mini2026.033——
DirectTarget Model=GPT-5-nano2026.032——
Sys. MsgTarget Model=GPT-5-nano2026.031——
Tool Know.Target Model=GPT-5-nano2026.031——
Imp. Instr.Target Model=GPT-5-nano2026.031——
Ignore Prev.Target Model=GPT-5-nano2026.030——
InjecagentTarget Model=GPT-5-nano2026.030——
AgentVigilVictim Model=DeepSeek, Defense=No Defense2026.05——39.2
AgentVigilVictim Model=DeepSeek, Defense=Tool Filter2026.05——0.4
AgentVigilVictim Model=DeepSeek, Defense=PI Detector2026.05——4.1
AgentVigilVictim Model=DeepSeek, Defense=Repeat2026.05——14.1
AgentVigilVictim Model=DeepSeek, Defense=Delimit2026.05——17.8
BenchmarkVictim Model=DeepSeek, Defense=No Defense2026.05——32.9
BenchmarkVictim Model=DeepSeek, Defense=Tool Filter2026.05——0.4
BenchmarkVictim Model=DeepSeek, Defense=PI Detector2026.05——3.3
BenchmarkVictim Model=DeepSeek, Defense=Repeat2026.05——12.7
BenchmarkVictim Model=DeepSeek, Defense=Delimit2026.05——15.3
IterInjectVictim Model=DeepSeek, Defense=No Defense2026.05——47.8
IterInjectVictim Model=DeepSeek, Defense=Tool Filter2026.05——0.4
IterInjectVictim Model=DeepSeek, Defense=PI Detector2026.05——4.1
IterInjectVictim Model=DeepSeek, Defense=Repeat2026.05——14.9
IterInjectVictim Model=DeepSeek, Defense=Delimit2026.05——18.8