Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?

arXiv:2607.25995 · cs.CR, cs.AI · Submitted 2026-07-28 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-07-28

Updated: 2026-08-31

Comments: Accepted at the Workshop on the Use of Large Language Models for Cybersecurity (LLMSec), co-located with ESORICS 2026

Code: https://github.com/dynatrace-research/vulncare

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 11× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Knowledge Graph — 4× in this paper · explained in 7 episodes
• Graph Construction — 3× in this paper · explained in 3 episodes
• RAG — 3× in this paper · explained in 3 episodes
• Analyzer — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Kubernetes Security Posture Management — 2× in this paper
• Provenance — 2× in this paper · explained in 4 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Introspection — 1× in this paper · explained in 2 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• KubeIntellect: A Modular LLM-Orchestrated Agent Framework for End-to-End Kubernetes Management
• Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
• Graphene: Infrastructure Security Posture Analysis with AI-generated Attack Graphs
• GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation
• How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench
• KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis
• MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
• Risk Assessment Graphs: Utilizing Attack Graphs for Risk Assessment
• A Systematic Study of LLM-Based Architectures for Automated Patching
• LLMSecConfig: An LLM-Based Approach for Fixing Software Container Misconfigurations
• MicroRemed: Benchmarking LLMs in Microservices Remediation
• AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs