Agentic AI Request Forgery (AARF) – New vulnerability class exploiting planner ➝ memory ➝ plugin chaining in MCP Server, MAS, LangChain, and A2A agents. Red Team playbooks, threat models, OWASP Top 10 proposal.
owasp multi-agent-systems red-teaming ai-security aarf llm-security genai-security agentic-ai agent-to-agent memory-poisoning agentic-ai-threat-model agentic-ai-architecture agentic-ai-vulnerability
-
Updated
May 12, 2025