When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
Researchers have introduced a new benchmark, MCP-TDP Security Benchmark, to evaluate a novel attack vector called Tool Description Poisoning (TDP) against LLM agents. This attack manipulates an agent's understanding by altering its tool's metadata, leading to severe vulnerabilities. In tests, leading models like GPT-4o showed nearly 100% attack success rates in high-risk scenarios, and standard defenses proved largely ineffective. AI
IMPACT This research highlights critical security flaws in LLM agents, potentially impacting the development and deployment of autonomous systems.