PT-2026-75327

TuxCare rebuilt langgraph-checkpoint to address 1 CVE. Fixed in 2.1.2.post3+tuxcare...

PT-2026-74856

TuxCare rebuilt langgraph-checkpoint to address 1 CVE. Fixed in 2.1.2.post1+tuxcare...

CVE-2026-48121: Improper Neutralization of Special Elements in Data Query Logic

@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers threadid, checkpointns, checkpointid from config.configurable are passed into MongoDB fi...

CLEANSTART-2026-IX44091 Security fixes in py3-langgraph-checkpoint 4.1.1-r0

Package py3-langgraph-checkpoint version 4.1.1-r0 fixes 1 vulnerabilities: ghsa-f4xh-w4cj-qxq8...

CLEANSTART-2026-EY20977 Security fixes in py3-langgraph-prebuilt 1.1.0-r0

Package py3-langgraph-prebuilt version 1.1.0-r0 fixes 2 vulnerabilities: ghsa-f4xh-w4cj-qxq8, ghsa-gr75-jv2w-4656...

PT-2026-85873

Package py3-langgraph-prebuilt version 1.1.0-r0 fixes 2 vulnerabilities: ghsa-f4xh-w4cj-qxq8, ghsa-gr75-jv2w-4656...

PT-2026-85922

Package py3-langgraph-checkpoint version 4.1.1-r0 fixes 1 vulnerabilities: ghsa-f4xh-w4cj-qxq8...

CLEANSTART-2026-QE28556 Security fixes for ghsa-f4xh-w4cj-qxq8, ghsa-gr75-jv2w-4656 applied in versions: 1.1.0-r0

Multiple security vulnerabilities affect the py3-langgraph-prebuilt package. These issues are resolved in later releases. See references for individual vulnerability details...

CLEANSTART-2026-VB75499 Security fixes for ghsa-f4xh-w4cj-qxq8 applied in versions: 4.1.1-r0

Security vulnerability affects the py3-langgraph-checkpoint package. This issue is resolved in later releases. See references for vulnerability details...

PT-2026-66790

Security vulnerability affects the py3-langgraph-checkpoint package. This issue is resolved in later releases. See references for vulnerability details...

PT-2026-66788

Multiple security vulnerabilities affect the py3-langgraph-prebuilt package. These issues are resolved in later releases. See references for individual vulnerability details...

LangGraph SDK has unsafe URL path construction

Summarylanggraph-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 addres...

LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading

SummaryLangGraph'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 tur...

PYSEC-2026-2573 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...

PYSEC-2026-2575 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...

PYSEC-2026-2574 LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution

Context A Remote Code Execution vulnerability exists in LangGraph's caching layer when applications enable cache backends that inherit from BaseCache and opt nodes into caching via CachePolicy. Prior to langgraph-checkpoint 4.0.0, BaseCache defaults to JsonPlusSerializerpicklefallback=True. When...

PT-2026-59231

Context A Remote Code Execution vulnerability exists in LangGraph's caching layer when applications enable cache backends that inherit from BaseCache and opt nodes into caching via CachePolicy. Prior to langgraph-checkpoint 4.0.0, BaseCache defaults to JsonPlusSerializerpickle fallback=True. When...

PT-2026-59232

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...

AI-Pentest

Auto Pentest Platform Platform otomasi penetration testing de...

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...