INCIDENT MAP

Browse / AI Framework and Platform Flaws / CVE-2025-68664

LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

CVE-2025-68664 · 2025-12-23 critical

Class
AI Framework and Platform Flaws (filed by a model that read the advisory)
Technique
Unsafe deserialisation
Also involves
Sensitive Data Disclosure
Affected
langchain-core (PyPI)
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
EPSS
42.9% chance of exploitation in 30 days

How it works, in short

Serialization does not escape dictionaries with the reserved lc key, so attacker-supplied data is later rebuilt as framework objects, which can expose secrets. (Our summary, written by a model. The source text is below.)

Details

Summary

A serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data.

Attack surface

The core vulnerability was in dumps() and dumpd(): these functions failed to escape user-controlled dictionaries containing 'lc' keys. When this unescaped data was later deserialized via load() or loads(), the injected structures were treated as legitimate LangChain objects rather than plain user data.

This escaping bug enabled several attack vectors:

Security hardening

This patch fixes the escaping bug in dumps() and dumpd() and introduces new restrictive defaults in load() and loads(): allowlist enforcement via allowed_objects="core" (restricted to serialization mappings), secrets_from_env changed from True to False, and default Jinja2 template blocking via init_validator. These are breaking changes for some use cases.

Who is affected?

Applications are vulnerable if they:

The most common attack vector is through LLM response fields like additional_kwargs or response_metadata, which can be controlled via prompt injection and then serialized/deserialized in streaming operations.

Impact

Attackers who control serialized data can extract environment variable secrets by injecting {"lc": 1, "type": "secret", "id": ["ENV_VAR"]} to load environment variables during deserialization (when secrets_from_env=True, which was the old default). They can also instantiate classes with controlled parameters by injecting constructor structures to instantiate any class within trusted namespaces with attacker-controlled parameters, potentially triggering side effects such as network calls or file operations.

Key severity factors:

Exploit example

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!

Security hardening changes (breaking changes)

This patch introduces three breaking changes to load() and loads():

Migration guide

No changes needed for most users

If you're deserializing standard LangChain types (messages, documents, prompts, trusted partner integrations like ChatOpenAI, ChatAnthropic, etc.), your code will work without changes:

from langchain_core.load import load

# Uses default allowlist from serialization mappings
obj = load(serialized_data)

For custom classes

If you're deserializing custom classes not in the serialization mappings, add them to the allowlist:

from langchain_core.load import load
from my_package import MyCustomClass

# Specify the classes you need
obj = load(serialized_data, allowed_objects=[MyCustomClass])

For Jinja2 templates

Jinja2 templates are now blocked by default because they can execute arbitrary code. If you need Jinja2 templates, pass init_validator=None:

from langchain_core.load import load
from langchain_core.prompts import PromptTemplate

obj = load(
    serialized_data,
    allowed_objects=[PromptTemplate],
    init_validator=None
)

> [!WARNING]
> Only disable init_validator if you trust the serialized data. Jinja2 templates can execute arbitrary Python code.

For secrets from environment

secrets_from_env now defaults to False. If you need to load secrets from environment variables:

from langchain_core.load import load

obj = load(serialized_data, secrets_from_env=True)

Credits

References

Source: GitHub Advisory Database, used under CC BY 4.0.