Metraipolis › archive › dc_a97c6773d515

CoSec: Benchmarking Agent Security in Communities — arXiv:2609.34790

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34790
License (as archived)
CC0-1.0
Archived
2026-10-07T21:02:57.797Z
SHA-256 of the archived text
63ac90375c39309f34ce8ae6f76f3b9f6f5251aadfd4d53ac805600c941c5adf
Stable URL of this page
https://metraipolis.com/documento/dc_a97c6773d515

How to cite

CoSec: Benchmarking Agent Security in Communities — arXiv:2609.34790 — arXiv (en), https://arxiv.org/abs/2609.34790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a97c6773d515 (Metraipolis archive dc_a97c6773d515, sha256 63ac90375c39309f34ce8ae6f76f3b9f6f5251aadfd4d53ac805600c941c5adf)
BibTeX
@misc{dca97c6773d515,
  title = {CoSec: Benchmarking Agent Security in Communities — arXiv:2609.34790},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34790},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a97c6773d515; sha256 63ac90375c39309f34ce8ae6f76f3b9f6f5251aadfd4d53ac805600c941c5adf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with changes in membership, roles, composition, and relationships. Agents must complete legitimate tasks and prevent unauthorized disclosure of protected information. Existing evaluations do not fully examine these risks in agent systems. We introduce \textbf{CoSec}, an executable benchmark for evaluating privacy and authorization enforcement in LLM agent systems operating within and across communities. CoSec contains 208 canonical scenarios spanning fixed and evolving boundaries, protected information belonging to the agent owner or other participants, and attacks through dialogue, environmental content, persistent memory, and composed workflows. CoSec executes complete agent systems with persistent sessions, memory, files and tools. It verifies information flows against the active authorization state using execution traces and artifacts. Across harness and model configurations, agents frequently complete benign tasks but violate privacy and authorization boundaries. Privacy behavior varies across harnesses, attack surfaces, and community states, revealing how memory, files, tools, and workflows can carry protected information beyond its authorized scope. These findings show that task utility does not imply privacy or authorization compliance and that authorization in community settings remains an unresolved security challenge for persistent LLM agents.

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/2609.34790 — 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 2026-10-07T20:29:03.161Z 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).