Tool · curated 21 Jul 2026
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
AI-Infra-Guard gives defenders a runnable open-source way to audit MCP servers and third-party agent skill packages as a supply chain — an attack surface at the center of enterprise agentic deployments where prompt injection and tool-poisoning attacks (and flaws like CVE-2025-49596) are systemic.
Tencent's Zhuque Lab released AI-Infra-Guard, an open-source multi-layer AI agent red-teaming framework, on June 30, 2026, described in an arXiv paper and published to GitHub. The framework matches a detection paradigm to each layer of an agent's attack surface: deterministic rule matching over 75+ components and 1,400+ vulnerability rules, LLM-driven agentic auditing of MCP servers and agent-skill packages (supply-chain auditing), multi-turn black-box agent red teaming, and a jailbreak harness with 26+ attack operators across sixteen datasets.