Check Point found 11 vulnerabilities across six agent frameworks — and argues the frameworks, not prompt injection, are the bug

The Register·high signalXBlueskyLinkedInCopy link

At Black Hat 2026, Check Point's Yarden Porat and Shahar Tal presented 11 vulnerabilities spanning LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework and Google ADK, showing that prompt-controlled content crosses the boundary into trusted framework logic itself. The bug classes are boringly conventional — insecure deserialization, SSRF, path traversal, use-after-free — which is precisely the point. A Microsoft Agent Framework checkpoint-deserialization flaw let one user plant a payload via prompt injection that fired when another user reloaded their session ($10,000 bounty); Google ADK shipped an unauthenticated HTTP API on by default that executed arbitrary Python and exposed service-account credentials ($3,133.70).