Lucene search
K

104 matches found

RedhatCVE
RedhatCVE
added 5 days ago7 views

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...

6CVSS5.3AI score0.0022EPSS
Exploits0References5
NVD
NVD
added 5 days ago6 views

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...

4.2CVSS0.0022EPSS
Exploits0References2
NVD
NVD
added 6 days ago9 views

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...

6.8CVSS0.00232EPSS
Exploits0References1
CVE
CVE
added 6 days ago8 views

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...

6.8CVSS6AI score0.00232EPSS
Exploits0References1
Positive Technologies
Positive Technologies
added 6 days ago11 views

PT-2026-50078

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...

4.2CVSS5.2AI score0.0022EPSS
Exploits0References3
The Hacker News
The Hacker News
added 2026/06/12 9:50 a.m.7 views

LangGraph Flaw Chain Exposes Self-Hosted AI Agents to Remote Code Execution

Cybersecurity researchers have disclosed details of three now-patched security flaws impacting LangGraph, including a critical vulnerability chain that could result in remote code execution. LangGraph is an open-source framework created by LangChain to build complex, stateful, and multi-agent...

7.8CVSS7.9AI score0.0444EPSS
Exploits2
OSV
OSV
added 2026/06/03 2:51 p.m.8 views

ROOT-APP-PYPI-CVE-2025-64439 CVE-2025-64439 in rootio-langgraph-checkpoint - Patched by Root

Root has patched CVE-2025-64439 in the rootio-langgraph-checkpoint package for Root:PyPI. Multiple fixed versions available...

7.4CVSS6.4AI score0.00835EPSS
Exploits0
IBM Security Bulletins
IBM Security Bulletins
added 2026/05/06 1:3 p.m.6 views

Security Bulletin: IBM App Connect Enterprise Certified Container DesignerAuthoring operands are vulnerable to loss of integrity, arbitrary code execution, denial of service and SSRF

Summary IBM App Connect Enterprise Certified Container Designer operands that use mapping assistance and Dashboard operands that use the App Connect Enterprise Agent are vulnerable to loss of integrity CVE-2026-28684, arbitrary code execution CVE-2026-28277, denial of service CVE-2026-40347 and...

7.2CVSS6.3AI score0.00427EPSS
Exploits1Affected Software1
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/04/07 12:15 p.m.2 views

Malicious code in @langgraphjs/toolkit (npm)

Package collects and sends sensitive system info to a hardcoded server. The package masquerades as a LangGraph JS utility but contains a malicious postinstall script. --- -= Per source details. Do not edit below this line.=- Source: amazon-inspector...

5.3AI score
Exploits0References2
The Hacker News
The Hacker News
added 2026/03/27 8:7 a.m.8 views

LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks

Cybersecurity researchers have disclosed three security vulnerabilities impacting LangChain and LangGraph that, if successfully exploited, could expose filesystem data, environment secrets, and conversation history. Both LangChain and LangGraph are open-source frameworks that are used to build...

9.8CVSS6.2AI score0.99959EPSS
Exploits56
RedhatCVE
RedhatCVE
added 2026/03/06 7:45 p.m.5 views

CVE-2026-28277

LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB both sync and async, via aiosqlite. In version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can...

6.8CVSS5.8AI score0.00427EPSS
Exploits0References1
vulnersOsv
vulnersOsv
added 2026/03/05 9:11 p.m.2 views

agent-nexus-cli (>=0.1.0 <=0.1.31), agentiva (>=0.1.0 <=0.1.5) potentially affected by CVE-2026-28277 via langgraph-checkpoint (>=4.0.0 <=4.0.1)

langgraph-checkpoint PYPI version =4.0.0, =0.1.0, =0.1.0, =0.1.5 Source cves: CVE-2026-28277 Source advisory: SNYK:PYTHON-LANGGRAPHCHECKPOINT-15433491...

7.2CVSS5.8AI score0.00427EPSS
Exploits0
Snyk
Snyk
added 2026/03/05 9:11 p.m.3 views

Deserialization of Untrusted Data

Overview langgraph-checkpoint is a library with base interfaces for LangGraph checkpoint savers. Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the msgpack-encoded checkpoints. An attacker can execute arbitrary code by supplying a crafted msgpack-encoded...

7.3CVSS6AI score0.00427EPSS
Exploits0References2
Snyk
Snyk
added 2026/03/05 9:11 p.m.4 views

Deserialization of Untrusted Data

Overview langgraph is a Building stateful, multi-actor applications with LLMs Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the msgpack-encoded checkpoints. An attacker can execute arbitrary code by supplying a crafted msgpack-encoded payload to the...

7.3CVSS6AI score0.00427EPSS
Exploits0References2
vulnersOsv
vulnersOsv
added 2026/03/05 9:11 p.m.5 views

adxp-cli (>=0.1.1 <=0.1.21), ag-ui-langgraph (>=0.0.14 <=0.0.29) +114 more potentially affected by CVE-2026-28277 via langgraph (>=1.0.0 <=1.0.10)

langgraph PYPI version =1.0.0, =0.1.1, =0.0.14, =0.0.2, =0.1.0, =0.2.1, =0.1.0, =0.1.0, =0.0.48, =0.0.54, =0.1.2, =0.1.4, =0.2.0 - chatlas-frontend =1.0.0 and more Source cves: CVE-2026-28277 Source advisory: SNYK:PYTHON-LANGGRAPH-15433492...

7.2CVSS5.4AI score0.00427EPSS
Exploits0
EUVD
EUVD
added 2026/03/05 8:19 p.m.7 views

EUVD-2026-9860

LangGraph checkpoint loading has unsafe msgpack deserialization...

6.8CVSS5.9AI score0.00427EPSS
Exploits0References1
vulnersOsv
vulnersOsv
added 2026/03/05 8:19 p.m.2 views

a-mailx (=0.1.0), a2a-client-handler (=0.1.0) +369 more potentially affected by CVE-2026-28277 via langgraph (>=0.1.15 <=1.0.1)

langgraph PYPI version =0.1.15, =0.1.5, =0.1.0, =0.1.1, =0.1.1, =0.0.1, =2.1.7, =0.0.2, =0.0.1, =0.1.1, =0.1.2, =0.0.4, =0.5.5 and more Source cves: CVE-2026-28277 Source advisory: OSV:GHSA-G48C-2WQR-H844...

7.2CVSS5.4AI score0.00427EPSS
Exploits0
Github Security Blog
Github Security Blog
added 2026/03/05 8:19 p.m.8 views

LangGraph checkpoint loading has unsafe msgpack deserialization

LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store for example, after a database compromise or other privileged write access to the persistence layer, they can...

7.2CVSS6.3AI score0.00427EPSS
Exploits0References4Affected Software1
OSV
OSV
added 2026/03/05 8:19 p.m.2 views

GHSA-G48C-2WQR-H844 LangGraph checkpoint loading has unsafe msgpack deserialization

LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store for example, after a database compromise or other privileged write access to the persistence layer, they can...

6.8CVSS6.4AI score0.00427EPSS
Exploits0References4
PyPA
PyPA
added 2026/03/05 8:16 p.m.5 views

PYSEC-2026-83

LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB both sync and async, via aiosqlite. In version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can...

7.2CVSS5.8AI score0.00427EPSS
Exploits0References1Affected Software1
Rows per page
Query Builder