AIDEFEND SecureFlow / SecureFlow Case Index

LangGraph Checkpointer SQLi and Deserialization RCE

• Autonomous Agents
• System Compromise & RCE
• Model Poisoning & Integrity

Check Point Research demonstrated a chain from a user-controlled LangGraph SQLite checkpointer filter key to a UNION-returned fake checkpoint row and unsafe MsgPack reconstruction. LangGraph's own advisory describes the deserialization issue as a defense-in-depth flaw normally requiring privileged checkpoint-store write access and says it knows of no practical path in existing deployments; the graph retains that disagreement explicitly. A Redis injection issue is parallel and is not connected to the SQLite RCE chain.