CVE-2026-27794 LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution

Medium 6.6 Published Updated

Attackers with write access to the cache backend can achieve remote code execution via unsafe pickle deserialization in LangGraph's caching layer.

Exploited in the wild
Not known
Login needed
An administrator
Attackable
Over the internet
Victim action needed
Not needed
Fix
Available

What is CVE-2026-27794?

CVE-2026-27794 is a medium-severity unsafe deserialization vulnerability in langchain-ai langgraph-checkpoint, published on 25 Feb 2026. An attacker needs administrator access to exploit it, with no action from the victim.

Official description

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.

Weakness: CWE-502

Which versions are affected by CVE-2026-27794?

3 open source packages ship an affected version, including langgraph-checkpoint.

PackageAffectedFixed in
langgraph-checkpoint PyPIAll versions4.0.0
langgraph-checkpoint PyPIAll versions4.0.0
langgraph-checkpoint PyPIAll versions4.0.0

How do I fix CVE-2026-27794?

Upgrade langgraph-checkpoint to 4.0.0 or later.

Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.

Is CVE-2026-27794 being exploited?

There is no known exploitation of CVE-2026-27794 in the wild and no public exploit code.

Sources

Also known as CLSA-2026-1780966309, ECHO-1e62-5969-14f5, GHSA-mhr3-j7m5-c7c9, PYSEC-2026-2574.

Is CVE-2026-27794 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free