Metraipolis › archive › dc_55a3a2ede4c2
AGATE: Provenance-Based Runtime Defense Against Compositional Attacks on LLM Agents — arXiv:2609.30830
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30830
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:09:19.610Z
- SHA-256 of the archived text
5ae2ce1d508a1d999221a50c1831b32d4204ff8c187f8f36986db326d04c8d1f- Stable URL of this page
https://metraipolis.com/documento/dc_55a3a2ede4c2
How to cite
AGATE: Provenance-Based Runtime Defense Against Compositional Attacks on LLM Agents — arXiv:2609.30830 — arXiv (en), https://arxiv.org/abs/2609.30830 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55a3a2ede4c2 (Metraipolis archive dc_55a3a2ede4c2, sha256 5ae2ce1d508a1d999221a50c1831b32d4204ff8c187f8f36986db326d04c8d1f)
BibTeX
@misc{dc55a3a2ede4c2,
title = {AGATE: Provenance-Based Runtime Defense Against Compositional Attacks on LLM Agents — arXiv:2609.30830},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30830},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55a3a2ede4c2; sha256 5ae2ce1d508a1d999221a50c1831b32d4204ff8c187f8f36986db326d04c8d1f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30830. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents can produce harmful effects through sequences of ordinary operations. Judging such actions requires establishing both the authority that permits them and the origin of the data they carry. We present AGATE, an authorization and data-provenance gate at instrumented agent-harness boundaries. Operator declarations and host approval events ground authorization; delegated actions are constrained by grants that bind to exact parameters, expire, and permit a limited number of uses. Source registration connects observed inputs to subsequent transfers, while an effect ledger tracks repeated requests. Deterministic checks make decisions without an LLM in the decision path and retain their grounds with execution evidence for forensic replay. Adapters integrate three production harnesses -- DeepSeek Harness, OpenCode, and OpenClaw -- without modifying host code, translating each host's native observation and veto points into a single shared gate interface; the judgment core is identical in all three, and only enforcement depth differs. Our evaluation combines 153 exercised attack-chain records with deployment, utility, and reconstruction experiments. The deployment observations expose how tool declarations and data checks govern business actions, including a bypass through parameter rewriting. Six of eleven benign file-processing scenarios contain denial events, revealing the utility cost of content-based provenance policies. Across 252 runs on 63 sanitized scenarios, replay agrees with live graph projections for all 63 scenarios on each of two platforms. These results establish the feasibility of provenance-based runtime judgment and identify content transformation, legitimate reuse, and observation coverage as concrete limits. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.30830 — 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 2026-10-08T01:42:25.532Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).