List your company

Indirect Prompt Injection on Agent Action Subset 2

0IRUser Review
-3.8822.3148.574.69May 14, 2026

Evaluation results

MethodLinks
User ReviewMemory regime=Tool, Model=Sonnet-4.62026.050
User ReviewMemory regime=External, Model=Sonnet-4.62026.050
User ReviewMemory regime=External, Model=GPT-5.42026.051
User ReviewMemory regime=External, Model=GPT-5.52026.051.5
User ReviewMemory regime=External, Model=Gemini-3.12026.051.5
User ReviewMemory regime=External, Model=Kimi-K2.62026.051.5
User ReviewMemory regime=Tool, Model=GPT-5.52026.052.5
User ReviewMemory regime=Tool, Model=GPT-5.42026.053
User ReviewMemory regime=External, Model=DeepSeek-v42026.055
Actor-CriticMemory regime=External, Model=Sonnet-4.62026.055.5
Actor-CriticMemory regime=Tool, Model=Sonnet-4.62026.056.5
User ReviewMemory regime=Tool, Model=Gemini-3.12026.0537
User ReviewMemory regime=Tool, Model=Kimi-K2.62026.0542.5
Actor-CriticMemory regime=External, Model=GPT-5.52026.0546.5
Actor-CriticMemory regime=External, Model=Gemini-3.12026.0559
User ReviewMemory regime=Tool, Model=DeepSeek-v42026.0559.5
Actor-CriticMemory regime=External, Model=GPT-5.42026.0561.5
Actor-CriticMemory regime=External, Model=Kimi-K2.62026.0565
Actor-CriticMemory regime=Tool, Model=Gemini-3.12026.0567
Actor-CriticMemory regime=Tool, Model=Kimi-K2.62026.0581
Actor-CriticMemory regime=External, Model=DeepSeek-v42026.0582.5
Actor-CriticMemory regime=Tool, Model=DeepSeek-v42026.0588.5
Actor-CriticMemory regime=Tool, Model=GPT-5.52026.0591.5
Actor-CriticMemory regime=Tool, Model=GPT-5.42026.0597