Metraipolis › archive › dc_11b4e76d50ad

Agent Name Collision Attacks in Multi-Agent Systems — arXiv:2609.27624

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27624
License (as archived)
CC0-1.0
Archived
2026-10-08T08:57:28.081Z
SHA-256 of the archived text
bd1dbeebb7649fd595b15c8bf0a029242f1c4ffe14252a03e24569b33d5ec4b7
Stable URL of this page
https://metraipolis.com/documento/dc_11b4e76d50ad

How to cite

Agent Name Collision Attacks in Multi-Agent Systems — arXiv:2609.27624 — arXiv (en), https://arxiv.org/abs/2609.27624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11b4e76d50ad (Metraipolis archive dc_11b4e76d50ad, sha256 bd1dbeebb7649fd595b15c8bf0a029242f1c4ffe14252a03e24569b33d5ec4b7)
BibTeX
@misc{dc11b4e76d50ad,
  title = {Agent Name Collision Attacks in Multi-Agent Systems — arXiv:2609.27624},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27624},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11b4e76d50ad; sha256 bd1dbeebb7649fd595b15c8bf0a029242f1c4ffe14252a03e24569b33d5ec4b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent hosts turn remote Agent Cards into local agents, tools, workflow targets, and broker routes. A2A defines the card's name as human-readable metadata, not as a stable identity, and specifies no collision semantics. The security failure begins when a host nevertheless uses that remote name as a local routing identifier. We traced registration through dispatch and ran isolated regression tests at seven pinned open-source revisions. Six client-style integrations selected an attacker-controlled peer's client or loopback endpoint for a request addressed to a trusted peer's name. A seventh, brokered implementation collapsed both peers onto one name-derived route; queue and access-control state determine whether the result is interception or denial. The common result is wrong-peer dispatch, not universal privilege inheritance. Synthetic credential and tool tests found no A-specific credential transfer in the tested client bindings and no direct transfer of A-owned tools. The broker path forwards a caller-configuration object; delegated identity or tokens reach B only if present and B can consume the route. Two other paths expose a later, model-mediated decision rather than direct execution authority. The necessary conditions assign different responsibilities to the protocol, implementations, and deployments. Hosts should route by an origin-bound stable identity, keep names presentational, and reject ambiguous aliases. The evidence establishes a recurring implementation vulnerability class, not a universal A2A protocol exploit or a count of vulnerable deployments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.MA).
Categorie arXiv: Cryptography and Security (cs.CR) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.27624 — 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 2026-10-08T08:03:18.950Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).