Skip to content
Review Open access

A Multi-Agent DevSecOps Framework for Intelligent Vulnerability Detection and Auto-Remediation

2026 · Journal of networking and network applications · 0 citations · 32 references

Abstract

This paper presents a multi-agent DevSecOps framework that integrates static code scanning, large language model (LLM) based security reasoning, automated repair generation, policy-as-code enforcement, and runtime monitoring into a unified event-driven pipeline. Five specialized agents collaborate through LangGraph shared state graphs: a Code Security Agent combining Semgrep rule matching with LLM contextual review, a Fix Agent generating reviewable candidate patches, a Policy Agent producing OPA Rego and Kubernetes NetworkPolicy files, and an Enforcement Agent operating in both CI gate and runtime response modes. Evaluation on a test application containing 50 planted vulnerabilities across Python code and infrastructure-as-code demonstrates that the combined Semgrep+LLM detection achieves 92.0% recall (F1=95.8%), compared to 34.0% for Semgrep alone, with zero false positives under the manually labeled test oracle. The Fix Agent commits candidate patches for 98.4% of detected vulnerabilities at an average of 35.5 seconds each. The Enforcement Agent correctly blocks non-compliant configurations and completes CI gate decisions in under 34 seconds. Runtime monitoring detects injection attacks, brute-force attempts, and unauthorized access with risk-proportional automated response within 42 seconds.

Read PDF

Similar papers

#artificial intelligence Preprint Sep 2026

AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents

AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adversarial content changes an agent's tool use or when the surrounding software contains vulnerabilities such as path traversal or command injection. We study authorized wh...

Wei-Da Liang, Shi Qiu, Zhun Wang et al. · 0 citations
Preprint Aug 2026

CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity

CyberLLM is presented, a multi-agent, LLM-orchestrated framework that autonomously detects vulnerabilities and executes remediations under a formal, runtime safety guard, and indicates that LLM agents can perform useful autonomous cyber-defense when wrapped in a deterministic, auditable safety envelope.

Nenad Petrovic, Oussama Jeddou, Feres Ben Fraj et al. · 0 citations
Open access Aug 2026

A Multi-Agent LLM Framework for Automated Software Testing

A multi-agent testing framework in which requirement analysis, test-case generation, sandboxed execution, and defect detection are delegated to four distinct agents, and in which detection rests on a composite rule combining the execution signal with the semantic judgment of a dedicated diagnostic agent.

Yuxuan Li · 0 citations
Review Open access Aug 2026

AgentCodeReview: Implementation and Comprehensive Benchmark Evaluation of a Multi-Agent Framework for Explainable Code Review and Automated Bug Repair

The AgentCodeReview system is presented, a multi-agent system that is able to conduct explainable code review and automated bug repair by leveraging software engineering agents with different code review tasks and its utility and extensibility to the field of explainable AI in software quality assurance are demonstrate...

B. N, T. L. Manasa · 0 citations
Review Aug 2026

ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

This work argues that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action consequence--while a denied dangerous objective can reappear across surface forms, tools, or turns.

Kai Wang, Zeming Wei, Biaojie Zeng et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale

VLoc Benchmark results establish vulnerability localization as a distinct repository-scale capability and provide a setting for studying both how security agents search for vulnerable code and when they should refrain from reporting it.

Aman Priyanshu, Supriti Vijay, Kimia Majd et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.