NetSight
hoch8.2

CVE-2026-44843

LangChain vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlists

Auswirkung

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.

Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, ohne Anmeldung, ohne Zutun eines Nutzers. Bei Erfolg: hohes Risiko, dass Daten ausgelesen werden, geringes Risiko, dass Daten oder Systeme verändert werden.

Betroffene Pakete

ÖkosystemPaketBetroffenBehoben in
piplangchain-core>= 1.0.0, <= 1.3.21.3.3

Betroffene Produkte · Langchain

ProduktBetroffene Versionen
Langchain
vor 0.3.85
ab 1.0.0 vor 1.3.3

Schwachstellenklasse

Referenzen