CVE-2026-27794

Описание

LangGraph Checkpoint defines the base interface for LangGraph checkpointers. Prior to version 4.0.0, a Remote Code Execution vulnerability exists in LangGraph's caching layer when applications enable cache backends that inherit from BaseCache and opt nodes into caching via CachePolicy. Prior to langgraph-checkpoint 4.0.0, BaseCache defaults to JsonPlusSerializer(pickle_fallback=True). When msgpack serialization fails, cached values can be deserialized via pickle.loads(...). Caching is not enabled by default. Applications are affected only when the application explicitly enables a cache backend (for example by passing cache=... to StateGraph.compile(...) or otherwise configuring a BaseCache implementation), one or more nodes opt into caching via CachePolicy, and the attacker can write to the cache backend (for example a network-accessible Redis instance with weak/no auth, shared cache infrastructure reachable by other tenants/services, or a writable SQLite cache file). An attacker must be able to write attacker-controlled bytes into the cache backend such that the LangGraph process later reads and deserializes them. This typically requires write access to a networked cache (for example a network-accessible Redis instance with weak/no auth or shared cache infrastructure reachable by other tenants/services) or write access to local cache storage (for example a writable SQLite cache file via permissive file permissions or a shared writable volume). Because exploitation requires write access to the cache storage layer, this is a post-compromise / post-access escalation vector. LangGraph Checkpoint 4.0.0 patches the issue.

A flaw was found in LangGraph Checkpoint. This vulnerability allows a remote attacker with write access to the cache backend to achieve remote code execution. This occurs when applications enable cache backends that inherit from BaseCache and opt nodes into caching via CachePolicy. If msgpack serialization fails, cached values can be deserialized using pickle.loads(...), leading to the execution of arbitrary code. Exploitation requires prior write access to the cache storage layer, making it a post-compromise escalation vector.