LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

6.6 · CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:H

EPSS

• CVE-2026-27794: 0.84% estimated exploitation activity in the next 30 days; percentile 57.78 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Context 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(picklefallback=True). When msgpack serialization fails, cached values can be deserialized via pickle.loads(...). Who is affected? 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 - 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) Example (enabling a cache backend and opting a node into caching): With picklefallback=True,…

Published by the source

25 Feb 2026, 22:59 UTC

Last modified by the source

13 Jul 2026, 16:43 UTC

Source last checked

26 Oct 2026, 13:36 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-mhr3-j7m5-c7c9

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-mhr3-j7m5-c7c9

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-27794

Advisory: LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution
IDs: CVE-2026-27794, GHSA-mhr3-j7m5-c7c9
Record: https://patchnext.com/advisories/cve-2026-27794 (revision 2, source checked 26 Oct 2026, 13:36 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.6)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: langgraph-checkpoint 4.0.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI langgraph-checkpoint: affected < 4.0.0; fixed in 4.0.0

## Suggested inspection (read-only)
- `python -m pip show langgraph-checkpoint`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on langgraph-checkpoint.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-mhr3-j7m5-c7c9 (OSV record GHSA-mhr3-j7m5-c7c9 lists affected ranges: PyPI langgraph-checkpoint >=0 <4.0.0 (fixed))
- Verified: https://github.com/advisories/GHSA-mhr3-j7m5-c7c9 (GitHub-reviewed advisory GHSA-mhr3-j7m5-c7c9 lists affected ranges: PyPI langgraph-checkpoint >=0 <4.0.0)

Commands are suggestions: review each one before running it.