Treating the Model as an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking Against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Modelsarxiv_agent_systems_researchNov 8, 2026
I Think, Therefore I Attack: Evaluating Thought Injection Attacks on Reasoning Agentsarxiv_agent_systems_researchNov 6, 2026
IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injectionarxiv_llm_reliabilityNov 5, 2026