---
cve: "CVE-2026-27794"
severity: "MEDIUM"
cvss: 6.6
epss: "70%"
vendor: "langchain-ai"
kev: false
exploited: false
published: "2026-02-25 18:23:40"
tags: [cve, security, medium]
source: tsecurity.de CVE-Dossier
exported: "2026-09-11T13:01:46+02:00"
---

# CVE-2026-27794

> 6.6 MEDIUM · 🧪 PoC

## Beschreibung

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.

## CVSS-Vektor

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

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Hoch | good |
| PR Privilegien | Hoch | good |
| UI Interaktion | Keine | bad |
| S Scope | Unverändert | good |
| C Vertraulichkeit | Hoch | bad |
| I Integrität | Hoch | bad |
| A Verfügbarkeit | Hoch | bad |

## Patch verfügbar (OSV)

- f91d79d0c86932ded6e3b9f195d5a0bbd5aef99c (Commit)

## Referenzen

- <https://github.com/langchain-ai/langgraph/security/advisories/GHSA-mhr3-j7m5-c7c9>
- <https://github.com/langchain-ai/langgraph/pull/6677>
- <https://github.com/langchain-ai/langgraph/commit/f91d79d0c86932ded6e3b9f195d5a0bbd5aef99c>
- <https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D4.0.0>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-27794) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_