Metraipolis › archive › dc_2e0e4e622014
MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents — arXiv:2611.01700
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01700
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:22:19.038Z
- SHA-256 of the archived text
add7604f1454723d65ad6c86cb062d3e6ecf8e04f65d42dd229e15f408fec067- Stable URL of this page
https://metraipolis.com/documento/dc_2e0e4e622014
How to cite
MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents — arXiv:2611.01700 — arXiv (en), https://arxiv.org/abs/2611.01700 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e0e4e622014 (Metraipolis archive dc_2e0e4e622014, sha256 add7604f1454723d65ad6c86cb062d3e6ecf8e04f65d42dd229e15f408fec067)
BibTeX
@misc{dc2e0e4e622014,
title = {MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents — arXiv:2611.01700},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01700},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e0e4e622014; sha256 add7604f1454723d65ad6c86cb062d3e6ecf8e04f65d42dd229e15f408fec067},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01700. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents often rely on persistent memory to retain user preferences and operational rules across sessions. However, this capability introduces a new safety risk: malicious instructions from messages, documents, or Web content can be retained in memory and influence future tasks even after the original attack content is removed. Existing attack success metrics, however, fail to capture who is affected and how attacks translate into downstream harm during otherwise normal task execution. We introduce MemHarmBench, a victim-centric benchmark for evaluating cross-session prompt injection in memory-persistent AI agents. MemHarmBench considers three categories of potential victims: users, workspace/project owners, and external stakeholders. Our evaluation first exposes an agent to malicious instructions and tests whether they are retained in memory. We then remove the attack content and initiate a new session with a legitimate task while preserving the agent's memory. We jointly evaluate whether the agent follows the attacker's intent, completes the legitimate task, and exhibits observable execution anomalies. Across multiple agent systems, we find that cross-session attacks can remain behaviorally stealthy: agents often complete tasks normally and exhibit no detectable anomalies while still making critical decisions aligned with the attacker's intent. By connecting malicious memory retention to downstream decisions and affected parties, MemHarmBench provides a systematic framework for exposing safety risks that conventional attack- and task-success metrics may overlook. We publicly release MemHarmBench at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01700 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:19:49.829Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).