ROOT-APP-PYPI-CVE-2026-48776 CVE-2026-48776 in rootio-langgraph-sdk - Patched by Root

Root has patched CVE-2026-48776 in the rootio-langgraph-sdk package for Root:PyPI. Multiple fixed versions available...

CVE-2026-14742

A flaw was found in langgraph. A remote attacker could exploit this vulnerability by manipulating the defaultcachekey argument within the freeze function of the Task Result Cache component. This manipulation leads to the use of a weak hash, which may result in limited information disclosure...

Authorization Bypass Through User-Controlled Key

Overview langgraph is a Building stateful, multi-actor applications with LLMs Affected versions of this package are vulnerable to Authorization Bypass Through User-Controlled Key due to a key collision in the defaultcachekey and freeze functions of langgraph/internal/cache.py, where freeze reduce...

CVE-2026-14742

A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function freeze of the file libs/langgraph/langgraph/internal/cache.py of the component Task Result Cache. This manipulation of the argument defaultcachekey causes use of weak hash. The attack is...

CVE-2026-14742 langchain-ai langgraph Task Result Cache _cache.py _freeze weak hash

A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function freeze of the file libs/langgraph/langgraph/internal/cache.py of the component Task Result Cache. This manipulation of the argument defaultcachekey causes use of weak hash. The attack is...

CVE-2026-14742

A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function freeze of the file libs/langgraph/langgraph/internal/cache.py of the component Task Result Cache. This manipulation of the argument defaultcachekey causes use of weak hash. The attack is...

EUVD-2026-41747

A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function freeze of the file libs/langgraph/langgraph/internal/cache.py of the component Task Result Cache. This manipulation of the argument defaultcachekey causes use of weak hash. The attack is...

CVE-2026-14742

The CVE affects langchain-ai langgraph up to 1.2.4. The vulnerability lies in the function _freeze in libs/langgraph/langgraph/_internal/_cache.py (Task Result Cache). Manipulating the argument default_cache_key causes use of a weak hash, enabling a possible remote attack. Exploitation is describ...

EUVD-2026-37289

LangGraph SDK has unsafe URL path construction...

LangGraph SDK has unsafe URL path construction

Summary langgraph-sdk constructs HTTP request paths for resource operations by interpolating caller-supplied identifier values into URL templates. Without sanitization of those values, identifiers that contain characters with special meaning in URL paths could cause the resulting request to addre...

GHSA-W39P-VH2G-G8G5 LangGraph SDK has unsafe URL path construction

Summary langgraph-sdk constructs HTTP request paths for resource operations by interpolating caller-supplied identifier values into URL templates. Without sanitization of those values, identifiers that contain characters with special meaning in URL paths could cause the resulting request to addre...

EUVD-2026-37140

LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading...

GHSA-FJQC-HQ36-QH5P LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading

Summary LangGraph's JsonPlusSerializer can reconstruct Python objects from JSON checkpoint payloads. Under conditions where someone could modify checkpoint bytes at rest in the backing store, the deserialization path could reconstruct objects beyond what the application expects, which could in tu...

Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')

Overview langgraph-sdk is a SDK for interacting with LangGraph API Affected versions of this package are vulnerable to Improper Limitation of a Pathname to a Restricted Directory 'Path Traversal' in the construction of HTTP request paths using unsanitized identifier values. An attacker can gain...

CVE-2026-48776

A flaw was found in the LangGraph Python SDK. This vulnerability allows a remote attacker with low privileges to manipulate URL paths by providing unsanitized input. This could result in unintended access, modification, or deletion of resources, potentially compromising data confidentiality and...

CVE-2026-48776

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. Versions 0.3.14 and prior have unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource...

CVE-2026-48775

A flaw was found in LangGraph. This vulnerability allows an attacker with high privileges and adjacent network access to modify checkpoint data. By manipulating these stored checkpoint bytes, an attacker can trigger insecure deserialization, leading to arbitrary code execution when the checkpoint...

CVE-2026-48776 LangGraph SDK has unsafe URL path construction

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. Versions 0.3.14 and prior have unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource...

CVE-2026-48775

LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB both sync and async, via aiosqlite. In versions 4.1.0 and prior, the JsonPlusSerializer can reconstruct Python objects from JSON checkpoint payloads. Under conditions where someone could modify...

CVE-2026-48775

LangGraph SQLite Checkpoint (JsonPlusSerializer) is vulnerable in 4.1.0 and earlier due to unsafe deserialization of JSON checkpoint payloads. If an unauthorized party can modify checkpoint bytes at rest in the backing store, the deserialization path could reconstruct objects beyond what the appl...