CxBOM: A Context Bill of Materials and Signed Tool-Definition Pinning for LLM Agents

An LLM agent's context window is assembled from parts with different origins: operator instructions, tool definitions published by third parties through the Model Context Protocol (MCP), retrieved documents, tool outputs and user turns. Scaled dot-product attention takes no provenance input, so inside a standard transformer a trust distinction between them is at most a learned tendency, not an enforced boundary. We design and implement two mechanisms outside the model: a record that evidences provenance where the context is assembled, and a proxy that enforces approval at the MCP boundary. The Context Bill of Materials (CxBOM) records, in a format based on CycloneDX, every component assembled into a window: its trust ring, provenance, content digest and the controls applied to it. A preview pinning proxy for MCP refuses server launches that differ from a signed operator approval and, in enforce mode, withholds tool definitions and server instructions that differ from it, including a definition changed on a re-listing mid-session. Of the 23 in-scope attacks in our threat model, this version refuses 14, each shown by a passing test, refuses 1 in part, and leaves 8 open. The emitter and proxy pass 1,691 of 1,692 cases in their own test suite (1 skipped), including randomized and fault-injection tests. On a 46,205-token reference session, the emitter gives every component the ring, token count and digest of an earlier emitter's published record, and assembles, tokenizes and emits it in a median of 75 ms on one machine. We also give a trust-ring model of context assembly that grounds the record's fields, and the Dual-Failure Multiplier, a hypothesis that accumulating untrusted demonstrations degrade task quality and safety together, with a design that tests part of its attack half. Effectiveness in deployment, forensic utility, cost and the hypothesis are not yet measured. Reference implementation: https://github.com/CXBOM/cxbom-reference (tag v0.3.0).

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-26
DOI
https://doi.org/10.5281/zenodo.23653996
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

CxBOM: A Context Bill of Materials and Signed Tool-Definition Pinning for LLM Agents

Richard Bird, Chris Hughes, Kyriakos Rock Lambros, Fred Wilmot et al.
Zenodo (CERN European Organization for Nuclear Research)
Adversarial Robustness in Machine Learning
preprint

CxBOM: A Context Bill of Materials and Signed Tool-Definition Pinning for LLM Agents

Richard Bird, Chris Hughes, Kyriakos Rock Lambros, Fred Wilmot, Peter Holcomb, Dan Sorensen, Helen Oakley
preprint en

Abstract

An LLM agent's context window is assembled from parts with different origins: operator instructions, tool definitions published by third parties through the Model Context Protocol (MCP), retrieved documents, tool outputs and user turns. Scaled dot-product attention takes no provenance input, so inside a standard transformer a trust distinction between them is at most a learned tendency, not an enforced boundary. We design and implement two mechanisms outside the model: a record that evidences provenance where the context is assembled, and a proxy that enforces approval at the MCP boundary. The Context Bill of Materials (CxBOM) records, in a format based on CycloneDX, every component assembled into a window: its trust ring, provenance, content digest and the controls applied to it. A preview pinning proxy for MCP refuses server launches that differ from a signed operator approval and, in enforce mode, withholds tool definitions and server instructions that differ from it, including a definition changed on a re-listing mid-session. Of the 23 in-scope attacks in our threat model, this version refuses 14, each shown by a passing test, refuses 1 in part, and leaves 8 open. The emitter and proxy pass 1,691 of 1,692 cases in their own test suite (1 skipped), including randomized and fault-injection tests. On a 46,205-token reference session, the emitter gives every component the ring, token count and digest of an earlier emitter's published record, and assembles, tokenizes and emits it in a median of 75 ms on one machine. We also give a trust-ring model of context assembly that grounds the record's fields, and the Dual-Failure Multiplier, a hypothesis that accumulating untrusted demonstrations degrade task quality and safety together, with a design that tests part of its attack half. Effectiveness in deployment, forensic utility, cost and the hypothesis are not yet measured. Reference implementation: https://github.com/CXBOM/cxbom-reference (tag v0.3.0).

Zenodo (CERN European Organization for Nuclear Research)
Optimo (Chile) (CL)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon