Researchers bypass six AI agent frameworks with a simple ‘Repeat-After-Me’ attack and find 253 MCP bugs
Researchers from Penn State, Université de Montpellier and Dartmouth tricked six agent frameworks into executing attacker-written tool calls via a text-repetition request, and with a fuzzer confirmed 253 bugs across 118 of 273 open-source MCP servers, according to CSO Online.