Containing the Autonomous Operator: A Defense-in-Depth Framework and Reference Architecture for Securing AI Agents on Kubernetes
cs.CR, cs.NI
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/kubernetes-sigs/agent-sandbox
Terminology
Sources
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
- Defeating Prompt Injections by Design
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