# Proof-of-Execution Memory: Defending LLM Agents Against Forged-Reasoning Attacks by Verifying What Actually Happened

arXiv: https://arxiv.org/abs/2608.16032 · HTML: https://mlsanity.com/paper/2608.16032/

## Key facts

- Cited by 2 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 20 of its 24 references that are in the map.
- First posted on arXiv 17 Aug 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, 20 of 20)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Memory Injection Attacks on LLM Agents via Query-Only Interaction](https://mlsanity.com/paper/2503.03704/) (2025)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents](https://mlsanity.com/paper/2503.00061/) (2025)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage](https://mlsanity.com/paper/2502.08966/) (2025)
- [A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory](https://mlsanity.com/paper/2510.02373/) (2025)
- [Formal Policy Enforcement for Real-World Agentic Systems](https://mlsanity.com/paper/2602.16708/) (2026)
- [A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle](https://mlsanity.com/paper/2604.16548/) (2026)
- [Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents](https://mlsanity.com/paper/2503.16248/) (2025)
- [Context manipulation attacks : Web agents are susceptible to corrupted memory](https://mlsanity.com/paper/2506.17318/) (2025)
- [Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses](https://mlsanity.com/paper/2607.05029/) (2026)
- [MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection](https://mlsanity.com/paper/2605.23723/) (2026)
- [SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems](https://mlsanity.com/paper/2606.12703/) (2026)
- [Reasoning-Style Poisoning of LLM Agents via Stealthy Style Transfer: Process-Level Attacks and Runtime Monitoring in RSV Space](https://mlsanity.com/paper/2512.14448/) (2025)
- [MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents](https://mlsanity.com/paper/2605.03482/) (2026)

## Built on by (most cited first, 2 of 2)

- [Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit](https://mlsanity.com/paper/2608.27427/) (2026)
- [From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents](https://mlsanity.com/paper/2610.15390/) (2026)

## Abstract (arXiv)

LLM agents are stateless and rely on external memory to carry context between steps. Because agents treat that memory as trustworthy, an adversary who can write to it can steer their behavior. The FARMA attack does this with no malicious command: it inserts fabricated entries into the agent's reasoning memory claiming a required safety step is already done, so the agent skips it. SENTINEL, the defense proposed with FARMA, scores entries against a fixed list of suspicious wordings; its authors note that an attacker who knows the list can reword the forgery and evade it, and leave this open. We show the gap is worse than stated. An automated attacker that simply asks a language model to reword the forgery evades SENTINEL on its first try, reducing its protection to zero on every model tested. We also find a capability paradox: the attack succeeds far more often on stronger models (98-100% on GPT-4o and GPT-4o-mini) than on Llama-3.1-8B (44%), because more capable agents follow reworded claims more faithfully, so the threat grows with capability. We propose Proof-of-Execution Memory (PoEM), which does not inspect memory at all. PoEM keeps a separate, tamper-evident, HMAC-chained ledger of the safety steps that actually executed, writable only by the trusted action layer, and allows a skip only if the ledger confirms real execution. An attacker can change what memory says but cannot forge a ledger entry for a step that never ran, so rewording no longer helps. Across three models and three scenarios, PoEM drives attack success to 0% while leaving legitimate operation intact (0% false positives in eight of nine cells, 1.7% in the ninth, within sampling noise), whereas SENTINEL wrongly blocks 33-50% of legitimate operations. PoEM also withstands attacks aimed at itself, adds microseconds of overhead, and works unchanged in a real LangChain agent. PoEM protects exactly the decisions it gates.