NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations

arXiv:2607.10490 · cs.CR, cs.LG · Submitted 2026-07-11 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-07-11

Updated: 2026-09-27

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 42× in this paper · explained in 2 episodes
• LLM judge — 21× in this paper · explained in 2 episodes
• Benchmarking — 5× in this paper · explained in 3 episodes
• Generative AI — 5× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Accountability — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Diagnostic Tools — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Guide to Attribute Based Access Control — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Text-to-SQL — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
• Artificial Intelligence for IT Operations (AIOPS) Workshop White Paper
• On the Opportunities and Risks of Foundation Models
• StruQ: Defending Against Prompt Injection with Structured Queries
• The Llama 3 Herd of Models
• Defending Against Indirect Prompt Injection Attacks With Spotlighting
• Mistral 7B
• MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
• AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
• Prompt Injection attack against LLM-integrated Applications
• A Systematic Mapping Study in AIOps
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Model evaluation for extreme risks
• The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
• ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
• Ethical and social risks of harm from Language Models
• Qwen2.5 Technical Report
• Defense Against Indirect Prompt Injection via Tool Result Parsing

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs