Langchain maintains a suite of large language model frameworks and integration libraries that have achieved significant adoption in AI application development, spanning Python, JavaScript, and experimental components. Vulnerabilities affecting this vendor skew strongly toward critical severity, concentrating in the core library, community integrations, and experimental extensions across both language implementations. The exposure recurs through structural weaknesses inherent to LLM orchestration: server-side request forgery where prompts or tool configurations trigger unintended external access, code and prompt injection where untrusted inputs flow into model contexts or execution chains, and unsafe deserialization in agent and tool-loading workflows. Defenders integrating Langchain should apply strict input validation at model boundaries, isolate LLM execution contexts, and monitor third-party tool and chain definitions carefully; live exploitation, severity, and exposure counts are shown alongside this summary.
The number and severity of CVEs published that impact products developed by Langchain over time
Signals from CVEs in this vendor scope (49 CVEs).
49 CVEs · Highest risk first
| CVE | Published | CVSS | Risk | KEV | Exploit |
|---|---|---|---|---|---|
CVE-2025-68664HIGH LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() | Dec 23, 2025 | 8.2 | 55 | NO | YES |
CVE-2023-29374CRITICAL In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method. | Apr 5, 2023 | 9.8 | 53 | NO | NO |
CVE-2023-46229HIGH LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server. | Oct 19, 2023 | 8.8 | 52 | NO | NO |
CVE-2026-44843HIGH LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run o | May 26, 2026 | 8.2 | 36 | NO | NO |
CVE-2025-2828CRITICAL A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.open | Jun 23, 2025 | 10.0 | 35 | NO | NO |
CVE-2024-8309CRITICAL A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthoriz | Oct 29, 2024 | 9.8 | 35 | NO | NO |
CVE-2026-48776CRITICAL 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 | Jun 16, 2026 | 9.1 | 34 | NO | NO |
CVE-2026-40190CRITICAL LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to 0.5.18, the LangSmith JavaScript/TypeScript SDK (langsmith) contains an incomplete prototy | Apr 10, 2026 | 9.8 | 34 | NO | NO |
CVE-2026-34070HIGH LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embed | Mar 31, 2026 | 7.5 | 33 | NO | NO |
CVE-2025-68665CRITICAL LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serializatio | Dec 23, 2025 | 9.1 | 31 | NO | NO |
Signals from CVEs in this vendor scope (49 CVEs).
An overview of all social media posts that mention a CVE ID that affects a product developed by Langchain.
Media articles that mention a CVE ID that affects a product developed by Langchain — matched by CVE ID, not by vendor name.