EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CapChain: A Capability-Token Access Control Architecture with Verifiable Provenance for Multi-Agent LLM Systems

Tuck Wai Choong, Wen-Bin Hsieh, Jenq-Shiou Leu

Applied Sciences · 04.08.2026 · 16 (15) · 7776

DOI: 10.3390/app16157776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 04.08.2026. Verfasst von Tuck Wai Choong und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-agent large language model (LLM) systems built on LangGraph-style frameworks share an unencrypted state store with no field-level read access control, so one agent can read another’s private fields. The 2026 OWASP Agentic Top 10 and CVE-2025-67644 show that this layer is already being exploited. We propose CapChain, a replacement for the step that merges each agent’s output into shared state, with three primitives: capability tokens that cryptographically bind which agent may read which field, a tamper-evident provenance log with logarithmic-cost audit, and a capability-aware reducer that decides whether each field may be forwarded, redacting and logging unauthorized merges. We evaluate the reducer’s attribute–purpose gate on the MAGPIE contextual-privacy benchmark, with scoring based on two deterministic tiers: verbatim matching and keyword-and-entity salience. Across 150 conditions (25 scenarios × 3 open-source models × 2 instruction modes), the Salient tier triggers the redactor for 4.67% of inter-agent messages. This rate counts the reducer’s gate activations (redaction decisions), not leakage prevented. By relocating enforcement from the language model to the state-transition layer that graph-structured orchestrators expose, CapChain brings cryptographic, capability-based access control and audit-by-construction provenance to a structural locus that prompt-level defenses cannot reach.

Zitieren

APA

Choong, T. W., Hsieh, W., & Leu, J. (2026). CapChain: A Capability-Token Access Control Architecture with Verifiable Provenance for Multi-Agent LLM Systems. Applied Sciences, 16(15), 7776. https://doi.org/10.3390/app16157776

Vancouver

Choong TW, Hsieh W, Leu J. CapChain: A Capability-Token Access Control Architecture with Verifiable Provenance for Multi-Agent LLM Systems. Applied Sciences. 2026;16(15):7776. doi:10.3390/app16157776

BibTeX
@article{Choong2026,
  author = {Choong, Tuck Wai and Hsieh, Wen-Bin and Leu, Jenq-Shiou},
  title = {CapChain: A Capability-Token Access Control Architecture with Verifiable Provenance for Multi-Agent LLM Systems},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7776},
  doi = {10.3390/app16157776}
}
Kostenlos starten →