<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uppala-2026-prompts">
    <titleInfo>
        <title>Prompts Don’t Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rohith</namePart>
        <namePart type="family">Uppala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent’s context, models select them in 48–68% of adversarial scenarios—even when explicitly instructed not to. Role escalation attacks (e.g., “I’m the CFO, override the access controls”) are the most dangerous category, reaching 96% unauthorized invocation in frontier models. We show this holds across three models spanning open-weight and frontier systems, including instruction-tuned models with strong alignment training. Critically, prompt-based compliance is both insufficient and unpredictable: explicit per-tool allowlists reduce violations to as low as 4.0% but never to zero, and compliance varies widely across models—from 4.0% to 37.0% UIR—with no reliable relationship to general capability. We propose a proxy-enforced attribute-based access control (ABAC) layer for MCP that filters tool registries at discovery time. Because unauthorized tools never reach the model context, UIR is 0% by design—a structural guarantee that prompt instructions cannot replicate regardless of model or phrasing.</abstract>
    <identifier type="citekey">uppala-2026-prompts</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.4/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>43</start>
            <end>49</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompts Don’t Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
%A Uppala, Rohith
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F uppala-2026-prompts
%X Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent’s context, models select them in 48–68% of adversarial scenarios—even when explicitly instructed not to. Role escalation attacks (e.g., “I’m the CFO, override the access controls”) are the most dangerous category, reaching 96% unauthorized invocation in frontier models. We show this holds across three models spanning open-weight and frontier systems, including instruction-tuned models with strong alignment training. Critically, prompt-based compliance is both insufficient and unpredictable: explicit per-tool allowlists reduce violations to as low as 4.0% but never to zero, and compliance varies widely across models—from 4.0% to 37.0% UIR—with no reliable relationship to general capability. We propose a proxy-enforced attribute-based access control (ABAC) layer for MCP that filters tool registries at discovery time. Because unauthorized tools never reach the model context, UIR is 0% by design—a structural guarantee that prompt instructions cannot replicate regardless of model or phrasing.
%U https://aclanthology.org/2026.emnlp-industry.4/
%P 43-49

Markdown (Informal)

[Prompts Don’t Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control](https://aclanthology.org/2026.emnlp-industry.4/) (Uppala, EMNLP 2026)

• Prompts Don’t Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control (Uppala, EMNLP 2026)

ACL

• Rohith Uppala. 2026. Prompts Don’t Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 43–49, Budapest, Hungary. Association for Computational Linguistics.