Check Point found 11 vulnerabilities across six agent frameworks, and the bug classes are boringly conventional.

LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework, and Google ADK, presented at Black Hat (The Register). Insecure deserialization, SSRF, path traversal, use-after-free. That's the point: prompt-controlled content crosses into trusted framework logic, and then it's just ordinary appsec. A Microsoft Agent Framework checkpoint-deserialization flaw let one user plant a payload via prompt injection that fired when a different 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). Your agent framework is a web application. Scan it like one.