---
cve: "CVE-2026-44843"
severity: "HIGH"
cvss: 8.2
epss: "41%"
vendor: "langchain-ai"
kev: false
exploited: false
published: "2026-05-26 21:16:39"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-12T12:13:39+02:00"
---

# CVE-2026-44843

> 8.2 HIGH · 🧪 PoC

## Beschreibung

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.

## CVSS-Vektor

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

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

## Patch verfügbar (OSV)

- 33a74aea3b0f563f926249977372d6935be2bce0 (Commit)
- 14b1a243e57dc07d3b1e7b77e8f76c232533a2e4 (Commit)

## Referenzen

- <https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-44843) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_