LangChain Vulnerabilities

pipLLM Frameworks

AI Threat Alert tracks 62 known vulnerabilities in LangChain, 23 rated critical — an AI/ML llm frameworks in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

77
Risk Score
62
Total CVEs
23
Critical
pip
Ecosystem
Nov 9, 2026
Last CVE
29%
Patch Rate
164d
Avg Time to Patch
149,524 stars25,131 forks743 issues3,161 dependentsLast push Nov 14, 2026
View on GitHub
OpenSSF Scorecard5.8/10

Known Vulnerabilities(62 total, page 1 of 3)

SeverityCVE IDSummaryCVSSPublished
MEDIUMCVE-2026-125386langchain4j-aideepin: IDOR exposes other users' RAG data5.3Nov 9, 2026MEDIUMCVE-2026-106119LangChain MongoDB: NoSQL injection exposes chat histories--Oct 6, 2026UNKNOWNCVE-2026-105799LangChain Redis: filter injection exposes cross-tenant docs--Oct 6, 2026HIGHGHSA-g28h-2cmm-rj9xlangchain-nvidia: local file read via VLM image paths7.5Sep 24, 2026HIGHCVE-2026-49042Camel: input validation flaw in LLM agent tool components7.3Jul 6, 2026MEDIUMCVE-2026-59152LangSmith SDK: arbitrary file read via TracingMiddleware5.0Jul 6, 2026MEDIUMCVE-2026-55443LangChain: path traversal exposes files outside agent root5.5Jun 22, 2026HIGHCVE-2026-55405langchain4j: SQL injection in vector store filters7.6Jun 17, 2026MEDIUMCVE-2026-48776LangGraph SDK: path traversal bypasses proxy-layer authz4.2Jun 16, 2026MEDIUMGHSA-gr75-jv2w-4656LangChain: path traversal exposes files outside sandbox5.1Jun 16, 2026HIGHCVE-2026-45134LangSmith: prompt deserialization enables SSRF + data leak7.1May 13, 2026HIGHCVE-2026-44843LangChain: deserialization poisons LLM chat history8.2May 8, 2026LOWCVE-2026-7847Langchain-Chatchat: predictable file IDs leak uploaded files2.6May 5, 2026LOWCVE-2026-7846Langchain-Chatchat: TOCTOU race allows silent file overwrite2.6May 5, 2026LOWCVE-2026-7845Langchain-Chatchat: weak image hash allows integrity bypass2.6May 5, 2026LOWCVE-2026-41488langchain-openai: SSRF via DNS rebinding in image token counter3.1Apr 24, 2026MEDIUMCVE-2026-41481LangChain: SSRF redirect bypass exposes internal endpoints6.5Apr 24, 2026MEDIUMGHSA-fv5p-p927-qmxrlangchain-text-splitters: SSRF bypass exposes cloud metadata6.5Apr 16, 2026MEDIUMCVE-2026-40190langsmith: prototype pollution enables auth bypass, RCE5.6Apr 10, 2026MEDIUMCVE-2026-40087LangChain: template injection leaks object attributes5.3Apr 9, 2026MEDIUMCVE-2024-2965langchain-community: DoS via recursive sitemap loop4.2Jun 6, 2024CRITICALCVE-2023-32785LangChain: prompt injection → SQL RCE (CVSS 9.8)9.8Oct 21, 2023HIGHCVE-2026-25750langsmith: security flaw enables exploitation8.1Mar 4, 2026MEDIUMCVE-2026-26019langchain_community: SSRF allows internal network access4.1Feb 11, 2026LOWCVE-2026-26013langchain-core: SSRF allows internal network access3.7Feb 10, 2026

Showing 1–25 of 62

Frequently asked questions

What is LangChain?

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

How many known vulnerabilities does LangChain have?

LangChain has 62 known CVEs, 23 of them critical, tracked from NVD and GitHub Advisory.

Which ecosystem is LangChain distributed in?

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

Where does the LangChain 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 LangChain?

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

Monitor LangChain in your stack

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

Start Monitoring