Metraipolis › archive › dc_da5d2874c455
Runtime Authorization for Resources Acquired by AI Agents — arXiv:2609.14744
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14744
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:47:36.531Z
- SHA-256 of the archived text
98ded0a2f1f52d1ce474ad178a9af2ea3e59b3e6acf7434727d3d4d8501cc4e6- Stable URL of this page
https://metraipolis.com/documento/dc_da5d2874c455
How to cite
Runtime Authorization for Resources Acquired by AI Agents — arXiv:2609.14744 — arXiv (en), https://arxiv.org/abs/2609.14744 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da5d2874c455 (Metraipolis archive dc_da5d2874c455, sha256 98ded0a2f1f52d1ce474ad178a9af2ea3e59b3e6acf7434727d3d4d8501cc4e6)
BibTeX
@misc{dcda5d2874c455,
title = {Runtime Authorization for Resources Acquired by AI Agents — arXiv:2609.14744},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14744},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da5d2874c455; sha256 98ded0a2f1f52d1ce474ad178a9af2ea3e59b3e6acf7434727d3d4d8501cc4e6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14744. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, budget, OAuth, mandate, and fulfillment checks can validate transaction conditions without deciding whether a returned resource may become usable authority. This post-fulfillment activation gap spans tool-mediated creation, inter-agent delegation, and agentic commerce. We present a provenance-bounded runtime authorization architecture. It quarantines acquired outputs, resolves their actual capabilities from authenticated provider evidence through a versioned resolver, and activates them only through a current activation transaction that checks the resolved manifest, provenance, epochs, and a downward-closed relational envelope over a typed resource-capability hypergraph. The envelope preserves correlated identity, effect, data, delegation, and graph-wide limits. Single-use effect permits are revalidated and consumed at effect linearization. Under explicit assumptions, we prove eight safety properties covering quarantine, backing, non-amplification, split non-evasion, crash/retry, refunds, epochs, and effect confinement. Across five resource classes, reference semantics accepted 20/20 benign traces and rejected 40/40 registered unsafe traces over 810 events; an independent checker agreed on 60 base and 40 refinement traces and rejected 89/89 tamper tests. Frozen Codex and Gemini Model Context Protocol (MCP) client components completed 54/54 deterministic local stdio calls. In a registered 18-case staged MCP-to-Docker composition, both benign paths completed, and none of the 16 unsafe paths added an unauthorized Docker start request. A five-source audit classified 1,248 field pairs across 32 units; no unit alone supplied a complete activation profile. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.14744 — 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 2026-10-15T22:29:03.213Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).