PYSEC-2026-1530 LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list method

Context A SQL injection vulnerability exists in LangGraph's SQLite checkpoint implementation that allows attackers to manipulate SQL queries through metadata filter keys. This affects applications that accept untrusted metadata filter keys not just filter values in checkpoint search operations...

LangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializer

SummaryPrior 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...

PYSEC-2026-1527 LangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializer

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...

PYSEC-2026-1529 LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStore

Summary LangGraph's SQLite store implementation contains SQL injection vulnerabilities using direct string concatenation without proper parameterization, allowing attackers to inject arbitrary SQL and bypass access controls. Details /langgraph/libs/checkpoint-sqlite/langgraph/store/sqlite/base.py...

PYSEC-2026-1528 LangGraph's SQLite store implementation has a SQL Injection Vulnerability

A SQL injection vulnerability exists in the langchain-ai/langgraph repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators $eq, $ne, $gt, $lt, $gte, $lt...

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...

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

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...

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...

sentinel

Sentinel — Agentic Code & System Quality Guardian Production-...

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...

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...

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...