# Forensic Trajectory Signatures for Agent Memory Poisoning Detection

arXiv: https://arxiv.org/abs/2606.30566 · HTML: https://mlsanity.com/paper/2606.30566/

## 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 18 of its 28 references that are in the map.
- First posted on arXiv 29 Jun 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, 18 of 18)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Memory Injection Attacks on LLM Agents via Query-Only Interaction](https://mlsanity.com/paper/2503.03704/) (2025)
- [Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections](https://mlsanity.com/paper/2602.15654/) (2026)
- [From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents](https://mlsanity.com/paper/2606.04329/) (2026)
- [Hidden in Memory: Sleeper Memory Poisoning in LLM Agents](https://mlsanity.com/paper/2605.15338/) (2026)
- [MemLineage: Lineage-Guided Enforcement for LLM Agent Memory](https://mlsanity.com/paper/2605.14421/) (2026)
- [TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection](https://mlsanity.com/paper/2510.11203/) (2025)
- [The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck](https://mlsanity.com/paper/2605.11039/) (2026)
- [MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning](https://mlsanity.com/paper/2605.26154/) (2026)
- [VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills](https://mlsanity.com/paper/2606.26524/) (2026)
- [TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling](https://mlsanity.com/paper/2605.27690/) (2026)
- [Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents](https://mlsanity.com/paper/2605.08442/) (2026)
- [PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications](https://mlsanity.com/paper/2208.04943/) (2022)
- [Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents](https://mlsanity.com/paper/2604.26274/) (2026)
- [MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents](https://mlsanity.com/paper/2605.03482/) (2026)
- [What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection](https://mlsanity.com/paper/2606.04425/) (2026)
- [Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents](https://mlsanity.com/paper/2604.04035/) (2026)
- [The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context](https://mlsanity.com/paper/2605.26778/) (2026)

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

- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control](https://mlsanity.com/paper/2608.28502/) (2026)

## Abstract (arXiv)

Whether a trajectory-based detector can observe the retrieval provenance of an agent memory-poisoning attack is governed by one architectural variable: retrieval observability, whether the agent's memory access produces a logged tool call. We formalise this as a framework-agnostic retrieval-to-action provenance graph, classify published attack families by their position relative to it, measure the resulting coverage property against collected agent traces, and then falsify the detector's standalone deployment, reversing our own earlier recommendation to use the signature as a pre-filter ahead of recipient-metadata gating. Under exclusive tool-mediated payload access a retrieval-before-exfiltration event is structurally forced. Across eight non-overlapping zero-event control cells we observe 0 violations in 289 eligible successes over 87 scenario configurations. The invariant is empirically unbroken, but on the clustering unit no registered cell certifies the preregistered <=0.10 upper bound (per-cell bounds 0.10-0.35); a post-hoc pool of two control arms nominally clears it but is not credited. When the scaffold delivers the payload implicitly the signature disappears; we had read this as agents declining an available retrieval, but a follow-up shows it tracks store content instead, and that behavioural reading is withdrawn. The detector is then falsified for standalone use. Benign memory-grounded sends are trajectory-isomorphic: false-positive rate 24.7-57.6% on a 13-model factorial (N=4,160), positive predictive value <=3.85% at 1% attack prevalence, and a recipient-metadata gate flags 129/129 legitimate external emails. Retrieval-before-send is an attack precondition, not a maliciousness predicate; its cross-validated AUC also reflects membership of a 22-vector feature codebook, not generalisation. Companion to arXiv:2605.08442; we release the corpus and scoring code.