{"data":{"id":"7841d8c5-79b0-4a76-aff7-e88c862260b9","title":"Researchers bypass 6 AI agent frameworks with a simple ‘Repeat-After-Me’ prompt","summary":"Researchers from Pennsylvania State University, Université Montpellier and Dartmouth College showed that a \"Repeat-After-Me\" prompt can make six AI agent frameworks, including LangGraph, Microsoft Agent Framework, AutoGen, Google's Agent Development Kit 2.0, AWS Strands Agents and CrewAI, run attacker-written tool calls. In a LangGraph 1.2.0 demonstration with Llama 3.1 8B, the tool executed before the model's refusal arrived. Their ToFu fuzzer also confirmed 253 bugs affecting 343 tools across 118 of 273 open-source MCP servers.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://www.csoonline.com/article/4233811/researchers-bypass-6-ai-agent-frameworks-with-a-simple-repeat-after-me-prompt.html","publishedAt":"2026-10-12T12:07:30.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":["prompt_injection","jailbreak"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Microsoft","Google","Amazon","Meta"],"affectedVendorsRaw":["LangGraph","Microsoft Agent Framework","AutoGen","Google Agent Development Kit 2.0","AWS Strands Agents","CrewAI","Llama 3.1 8B","Ollama","Model Context Protocol (MCP) servers"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-12T12:07:30.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":["integrity","confidentiality","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":null,"atlasIds":["AML.T0051","AML.T0054"]}}