Metraipolis › archive › dc_c818ab820802

AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents — arXiv:2609.32915

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32915
License (as archived)
CC0-1.0
Archived
2026-10-07T21:00:47.334Z
SHA-256 of the archived text
f4ea922316e23a474490bc19a39ccad2059062d4988bd70b56d7a6b4c6f18ed2
Stable URL of this page
https://metraipolis.com/documento/dc_c818ab820802

How to cite

AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents — arXiv:2609.32915 — arXiv (en), https://arxiv.org/abs/2609.32915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c818ab820802 (Metraipolis archive dc_c818ab820802, sha256 f4ea922316e23a474490bc19a39ccad2059062d4988bd70b56d7a6b4c6f18ed2)
BibTeX
@misc{dcc818ab820802,
  title = {AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents — arXiv:2609.32915},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32915},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c818ab820802; sha256 f4ea922316e23a474490bc19a39ccad2059062d4988bd70b56d7a6b4c6f18ed2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Browser-use agents often carry information in their context as they move between websites. While it may be necessary for task completion, it also creates a privacy risk, especially when the information contains a private fact regarding the user. For example, an agent may learn a user's affiliation after reading a membership record. If it later selects a registration option specific to that affiliation on another website instead of a general option, the information gets leaked. In this work, we define and study behavioural side-channel leakage in browser-use agents, where an agent's actions inadvertently reveal private information (secret) retained from a prior website, despite an explicit instruction not to disclose it. We introduce AgentTell, a benchmark of 20 scenarios and 100 tasks in which an agent acquires a secret on one website and then completes a task on another website that offers secret-specific actions alongside a general action that reveals nothing. Our evaluation across 9,760 sessions on six backbones shows that agents carrying a secret reveal it through their actions in 61.1% of sessions. Even when agents explicitly state in memory that the secret must not be shared, they still reveal it in 56.7% of those sessions. Moreover, in 34.5% of leaking sessions, their final responses falsely assure users that the secret was not disclosed. These findings show that agents often fail to recognize side-channel leakage as a privacy risk.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32915 — 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 2026-10-07T20:29:02.502Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).