vibehacker
News
CSO Online ·

Repeat-After-Me: six agent frameworks run attacker tool calls the model only echoed

Penn State, Montpellier, and Dartmouth showed LangGraph, AutoGen, Google ADK 2.0, AWS Strands, Microsoft Agent Framework, and CrewAI will execute a structured tool call if the model is prompted to echo it—even when the model later refuses. Their ToFu fuzzer also confirmed 253 bugs across 118 open-source MCP servers, including 64 path-traversal and three command-injection flaws.

More news

View all

Spotted something we missed? Start a thread.