# Structurally Close, Temporally Distant: Measuring Security Exposure in Long-Horizon LLM Agents

arXiv: https://arxiv.org/abs/2609.05911 · HTML: https://mlsanity.com/paper/2609.05911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 5 Sep 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, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems](https://mlsanity.com/paper/2403.04960/) (2024)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective](https://mlsanity.com/paper/2409.19091/) (2024)
- [Attention Tracker: Detecting Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2411.00348/) (2024)
- [RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage](https://mlsanity.com/paper/2502.08966/) (2025)
- [UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats](https://mlsanity.com/paper/2001.01525/) (2020)
- [Practical Whole-System Provenance Capture](https://mlsanity.com/paper/1711.05296/) (2017)
- [Runtime Analysis of Whole-System Provenance](https://mlsanity.com/paper/1808.06049/) (2018)

## Abstract (arXiv)

Long-horizon LLM agents interact with untrusted content, persistent memory, external state, and sensitive tools. Existing analyses often characterize attacks by the number of execution steps between malicious input and a downstream action. We show that temporal remoteness can overstate security separation in stateful agents. We introduce a provenance-aware execution graph linking agent events through deterministic state, identifier, and tool provenance, and define influence distance DI as the shortest structural path from an untrusted source to a sensitive action. We compare it with sequence distance DT, the shortest injection--sink path in the ordered trajectory. Since the influence graph contains every sequence edge, DI ≤ DT; Gap=DT-DI measures the separation hidden by step count. Across 454 injection--sink pairs from 360 long-horizon AgentDojo trajectories over OpenAI's textttgpt-4o-mini and textttgpt-4o and Claude's Haiku 4.5 and Sonnet 4.6, Gap>0 for 96.9% of pairs, with a median gap of 9 hops; 91.0% remain decoupled after removing the largest provenance-only edge class. On AgentDojo's banking suite, 33.8% of 231 pairs from 377 trajectories decouple through different provenance mechanisms. Among 274 OpenAI pairs, Gap does not independently predict attack success after controlling for DT, attack family, and backend (βGap=0.066, p=.088). At matched thresholds k=2,3, a deterministic DI-based pre-execution gate blocks five attack sinks missed by a sequence-only gate with no additional benign blocking, although the paired gain is not significant (p=.0625). Execution structure therefore reveals proximity hidden by step count and can support targeted runtime intervention. We measure candidate influence pathways rather than causal attribution.