Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/CodeLion/OpenEvolve
Terminology
Sources
- Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
- IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization
- Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
- Do Reasoning LLMs Refuse What They Infer in Long Contexts?
- D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Assessing Automated Prompt Injection Attacks in Agentic Environments
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
- Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation
- Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
- Automatic and Universal Prompt Injection Attacks against Large Language Models
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
- Illuminating search spaces by mapping elites
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Ignore Previous Prompt: Attack Techniques For Language Models
- RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
- Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection
- MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems