# NEXUS: Structured Runtime Safety for Tool-Using LLM Agents

arXiv: https://arxiv.org/abs/2607.19356 · HTML: https://mlsanity.com/paper/2607.19356/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 15 of 15)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback](https://mlsanity.com/paper/2601.10156/) (2026)
- [RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage](https://mlsanity.com/paper/2502.08966/) (2025)
- [VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation](https://mlsanity.com/paper/2510.05156/) (2025)
- [Enforcing Temporal Constraints for LLM Agents](https://mlsanity.com/paper/2512.23738/) (2025)
- [LLM Agents Should Employ Security Principles](https://mlsanity.com/paper/2505.24019/) (2025)
- [ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection](https://mlsanity.com/paper/2604.11790/) (2026)
- [Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents](https://mlsanity.com/paper/2601.17549/) (2026)
- [Trusted AI Agents in the Cloud](https://mlsanity.com/paper/2512.05951/) (2025)

## Built on by (most cited first, 1 of 1)

- [SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment](https://mlsanity.com/paper/2608.07639/) (2026)

## Abstract (arXiv)

Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural EXecution Utility and Safety), a structured-plan safety monitor that applies a formal intervention policy to select among four actions: allow, block, request confirmation, or request revision. NEXUS combines deterministic safety rules, argument-level inspection, and a calibrated logistic-regression risk score for graded escalation. On a 128-instance synthetic benchmark, NEXUS achieves an F1 score of 0.949 and a 4-class intervention accuracy of 0.6406, outperforming rule-only intervention selection by 27.3 percentage points. It also improves over rule-only on R-Judge (F1 = 0.861 vs. 0.849), matches rule-only on AgentHarm due to threat-model limits, and achieves 0% ASR at 99% control allow on IPI. On the rule-blind NEXUS-Stress benchmark, NEXUS reaches an F1 score of 0.881, highlighting the difficulty of fine-grained intervention routing. With 0.205 ms median latency, NEXUS adds under 0.1% overhead to typical agent loops. Code, benchmarks, and the calibrated risk scorer are publicly released.