Oriel — AI & technology worth noticing, every day.

Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming

Paper · https://arxiv.org/abs/2606.31227

The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and the language models themselves, has outpaced the security tooling available to defend it. We present AI-Infra-Guard, an open-source framework that organizes AI red teaming around a single observation: the attack surface of an AI agent is stratified across layers (infrastructure, protocol/tool, agent behavior, and model), and no single detection paradigm fits all of them. The framework therefore matches a paradigm to each layer, from deterministic rule matching over 75+ AI components and 1{,}400+ vulnerability rules, through LLM-driven agentic auditing of MCP servers and agent-skill packages and multi-turn black-box agent red teaming, to a jailbreak harness with 26+ attack operators over sixteen datasets. To our knowledge it is the only open-source framework to span all of these, including supply-chain auditing of the agent skills that increasingly extend AI agents. We release AI-Infra-Guard as open source so that layer-paradigm matching can serve as a practical foundation for agent security and a shared base for the community to build on.

First seen by Oriel on .

AI summary

This paper introduces AI-Infra-Guard, an open-source framework for red teaming AI agents across infrastructure, protocols and tools, agent behavior, and models.

  • AI-Infra-Guard organizes agent security around four layers: infrastructure, protocol/tool, agent behavior, and model.
  • Its infrastructure scanner covers 75+ AI components and 1,400+ vulnerability rules using deterministic rule matching.
  • LLM-driven auditing evaluates MCP servers and agent-skill packages, including supply-chain risks affecting extensible AI agents.
  • Multi-turn black-box red teaming targets agent behavior, while a jailbreak harness provides 26+ attack operators across sixteen datasets.
  • The framework matches different detection paradigms to each layer and is released as a shared open-source foundation for agent security research.

#ai agents #red teaming #mcp #supply chain security

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 12, latest observation ; -1 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 2, latest observation ; 0 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2606.31227https://arxiv.org/abs/2606.31227 Read discussion