AgentShield Hybrid Runtime Firewall Architecture for Secure Tool Governance in Agentic Large Language Model Systems

The Agentic large language model (LLM) systems introduce a critical security boundary in which modelgenerated reasoning can trigger consequential external tool actions.This paper presents AgentShield-FW, a hybrid runtime firewall that separates reasoning from execution authority through typed Action Intent Objects, deterministic policy enforcement, classifier-assisted risk assessment, verifier-based route correction, approval and sandbox controls, and tamper-evident auditing.Evaluation combined a 20,000-case deterministic AAF-Bench generator, a leakagecontrolled public corpus, authorization-specific governance tests, adaptive adversarial evaluation, and interactive AgentDojo execution.From 56,155 normalized public records, exact-content deduplication retained 26,129 Clean V2 samples, including a held-out test set of 2,613 cases.On this set, AgentShield-FW achieved 1.77% attack success rate, 98.23% attack blocking, 98.16% F1, 95.29% balanced accuracy, and 97.05% safe completion.A bounded white-box adaptive evaluation produced 0/310 successful malicious trajectories under the specified mutation budget.On the official AgentDojo v1.2.2 subset, injection-task success decreased from 33.33% without protection to 0%, and unsafe canonical tool execution decreased from 92.86% to 0%.However, benign task success decreased from 58.33% to 16.67%, revealing substantial over-blocking.Verifier-specific analysis similarly showed improved malicious containment but measurable benign escalation and route-correctness degradation.The results demonstrate that actionlevel runtime mediation can strongly constrain unsafe agent behaviour while preserving reproducible governance evidence, but they also identify a significant security-utility trade-off that must be addressed before utility-preserving production deployment.

Authors

Institutions

Publication Details

Journal
International journal of intelligent engineering and systems
Published
2026-11-17
DOI
https://doi.org/10.22266/ijies2026.1231.11
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AgentShield Hybrid Runtime Firewall Architecture for Secure Tool Governance in Agentic Large Language Model Systems

Nada Abdulkareem Hameed, Azhar Hasan Nsaif, Uday Kareem Hussein Al-Saadi
International journal of intelligent engineering and systems
Adversarial Robustness in Machine Learning
article

AgentShield Hybrid Runtime Firewall Architecture for Secure Tool Governance in Agentic Large Language Model Systems

Nada Abdulkareem Hameed, Azhar Hasan Nsaif, Uday Kareem Hussein Al-Saadi
article en

Abstract

The Agentic large language model (LLM) systems introduce a critical security boundary in which modelgenerated reasoning can trigger consequential external tool actions.This paper presents AgentShield-FW, a hybrid runtime firewall that separates reasoning from execution authority through typed Action Intent Objects, deterministic policy enforcement, classifier-assisted risk assessment, verifier-based route correction, approval and sandbox controls, and tamper-evident auditing.Evaluation combined a 20,000-case deterministic AAF-Bench generator, a leakagecontrolled public corpus, authorization-specific governance tests, adaptive adversarial evaluation, and interactive AgentDojo execution.From 56,155 normalized public records, exact-content deduplication retained 26,129 Clean V2 samples, including a held-out test set of 2,613 cases.On this set, AgentShield-FW achieved 1.77% attack success rate, 98.23% attack blocking, 98.16% F1, 95.29% balanced accuracy, and 97.05% safe completion.A bounded white-box adaptive evaluation produced 0/310 successful malicious trajectories under the specified mutation budget.On the official AgentDojo v1.2.2 subset, injection-task success decreased from 33.33% without protection to 0%, and unsafe canonical tool execution decreased from 92.86% to 0%.However, benign task success decreased from 58.33% to 16.67%, revealing substantial over-blocking.Verifier-specific analysis similarly showed improved malicious containment but measurable benign escalation and route-correctness degradation.The results demonstrate that actionlevel runtime mediation can strongly constrain unsafe agent behaviour while preserving reproducible governance evidence, but they also identify a significant security-utility trade-off that must be addressed before utility-preserving production deployment.

International journal of intelligent engineering and systemsVol. 19(12)
Mustansiriyah University (IQ), Al Mansour University College (IQ), Ministry of Education (IQ)
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