LangGraph Vulnerabilities

pipLLM Frameworks

AI Threat Alert tracks 20 known vulnerabilities in LangGraph — an AI/ML llm frameworks in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

23
Risk Score
20
Total CVEs
0
Critical
pip
Ecosystem
Oct 28, 2026
Last CVE
77%
Patch Rate
9d
Avg Time to Patch
44,976 stars7,759 forks480 issues4,151 dependentsLast push Nov 15, 2026
View on GitHub

Known Vulnerabilities(20 total, page 1 of 1)

SeverityCVE IDSummaryCVSSPublished
HIGHCVE-2026-118668LangGraph API: Store namespace rewrite bypass in JS auth--Oct 28, 2026MEDIUMCVE-2026-118667LangGraph SDK: path traversal in v3 stream helpers4.3Oct 28, 2026MEDIUMCVE-2026-115883LangGraph stores: namespace label injection crosses tenants--Oct 23, 2026MEDIUMCVE-2026-115885LangGraph CLI: deploy --verbose leaks registry token in logs5.4Oct 23, 2026HIGHCVE-2026-104873LangGraph SDK: auth decorator flaw enables cross-user access--Oct 2, 2026HIGHCVE-2026-55253LangGraph Mongo: NoSQL injection exposes tenant data7.7Aug 20, 2026MEDIUMCVE-2026-55235langgraph-api: loopback webhook bypasses cross-user auth5.9Aug 19, 2026MEDIUMCVE-2026-55236LangGraph API: authz bypass leaks assistant config5.9Aug 19, 2026MEDIUMCVE-2026-71433LangGraph Checkpoint: prefix match leaks cross-tenant data5.3Aug 6, 2026LOWCVE-2026-14742LangGraph: weak hash in task cache risks poisoning3.1Jul 5, 2026MEDIUMCVE-2026-48776LangGraph SDK: path traversal bypasses proxy-layer authz4.2Jun 16, 2026MEDIUMCVE-2026-48775LangGraph SQLite: deserialization RCE at checkpoint load6.8Jun 16, 2026MEDIUMCVE-2026-48121LangGraph MongoDB: NoSQL injection leaks tenant checkpoints6.7Jun 12, 2026HIGHCVE-2026-44504Aegra: cross-tenant IDOR hijacks user thread data--May 7, 2026HIGHCVE-2025-64104langgraph-checkpoint-sqlite: SQL Injection exposes database7.3Oct 29, 2025HIGHCVE-2025-64439langgraph-checkpoint: Deserialization enables RCE--Nov 5, 2025HIGHCVE-2025-67644langgraph-checkpoint-sqlite: SQL Injection exposes database7.3Dec 10, 2025MEDIUMCVE-2026-27794langgraph-checkpoint: Deserialization enables RCE6.6Feb 25, 2026MEDIUMCVE-2026-28277langgraph: Deserialization enables RCE6.8Mar 5, 2026HIGHCVE-2025-8709langgraph-checkpoint-sqlite: SQL Injection exposes database7.3Oct 26, 2025

Frequently asked questions

What is LangGraph?

LangGraph is an AI/ML llm frameworks tracked by AI Threat Alert for security vulnerabilities in the pip ecosystem.

How many known vulnerabilities does LangGraph have?

LangGraph has 20 known CVEs, tracked from NVD and GitHub Advisory.

Which ecosystem is LangGraph distributed in?

LangGraph is distributed via the pip ecosystem and categorized as llm frameworks.

Where does the LangGraph vulnerability data come from?

Vulnerability data is sourced from NVD and GitHub Advisory, enriched with CVSS, EPSS, exploit signals, and patch status for each CVE.

How do I assess the risk of LangGraph?

Review each CVE below — every entry shows CVSS severity, EPSS exploit probability, exploitation signals, and whether a patched version is available.

Monitor LangGraph in your stack

Get instant alerts when new vulnerabilities affect LangGraph. CISO analysis, ATLAS technique mappings, and compliance reports included.

Start Monitoring