# LangChain vulnerabilities Source: https://junglewise.ai/threats/vendors/langchain Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 9 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/vendors/langchain.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 21 vulnerabilities in LangChain: 0 in the last 7 days and 7 in the last 90 days, 1 of them critical and 0 exploited in the wild. The most recent, CVE-2026-118668, was published on 28 October 2026. 4 vulnerabilities in the last four weeks, up 33% on the four before (3). 2 technologies have a page of their own. ## Counts - Last 7 days: 0 - Last 30 days: 4 - Last 90 days: 7 - All time: 21 (1 critical, 0 exploited in the wild) ## About LangChain Framework for building applications with large language models through composable components and chains. ## Latest LangChain vulnerabilities - [CVE-2026-118668: LangGraph API JavaScript custom authentication namespace bypass](https://junglewise.ai/threats/cve-2026-118668-langgraph-api-implements-the-langgraph-api-for-rapid-development) (high, CVSS 4, published 28 Oct 2026) - [CVE-2026-118667: LangChain LangGraph path traversal in RemoteGraph streaming](https://junglewise.ai/threats/cve-2026-118667-langgraph-python-sdk-is-used-to-connect-to-running-langgraph-api) (medium, CVSS 4.3, published 28 Oct 2026) - [CVE-2026-115885: LangGraph CLI credential exposure in verbose mode](https://junglewise.ai/threats/cve-2026-115885-the-langgraph-cli-is-the-official-command-line-interface-for) (medium, CVSS 5.4, published 23 Oct 2026) - [CVE-2026-115883: LangGraph checkpoint savers namespace validation bypass in SQLite and Postgres](https://junglewise.ai/threats/cve-2026-115883-langgraph-checkpoint-savers-provide-postgres-and-sqlite-backed) (medium, CVSS 4, published 23 Oct 2026) - [CVE-2026-105799: LangChain @langchain/redis RediSearch injection](https://junglewise.ai/threats/cve-2026-105799-langchain-is-a-framework-for-building-llm-powered-applications) (medium, CVSS 4, published 6 Oct 2026) - [CVE-2026-104873: LangChain LangGraph Python SDK resource authorization bypass](https://junglewise.ai/threats/cve-2026-104873-langgraph-python-sdk-is-used-to-connect-to-running-langgraph-api) (high, CVSS 4, published 2 Oct 2026) - [CVE-2026-55253: LangChain MongoDB NoSQL injection in list/search methods](https://junglewise.ai/threats/cve-2026-55253-langchain-mongodb-nosql-injection-in-list-search-methods) (high, CVSS 7.7, published 14 Sep 2026) - [CVE-2026-48121: LangChain LangGraph NoSQL injection in MongoDBSaver](https://junglewise.ai/threats/cve-2026-48121-langchain-langgraph-nosql-injection-in-mongodbsaver) (medium, CVSS 6.7, published 4 Aug 2026) - [CVE-2026-25528: PYSEC-2026-2584 - LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection](https://junglewise.ai/threats/cve-2026-25528-langchain-langsmith-sdk-server-side-request-forgery-via-tracing) (low, CVSS 3.1, published 13 Jul 2026) - [CVE-2026-59152: LangChain LangSmith SDK arbitrary file read in TracingMiddleware](https://junglewise.ai/threats/cve-2026-59152-langchain-langsmith-sdk-arbitrary-file-read-in-tracingmiddleware) (medium, CVSS 5, published 6 Jul 2026) - [CVE-2026-48776: LangChain LangGraph SDK path traversal in URL construction](https://junglewise.ai/threats/cve-2026-48776-langchain-langgraph-sdk-path-traversal-in-url-construction) (medium, CVSS 4.2, published 17 Jun 2026) - [CVE-2026-48775: LangChain LangGraph unsafe deserialization in JsonPlusSerializer](https://junglewise.ai/threats/cve-2026-48775-langchain-langgraph-unsafe-deserialization-in-jsonplusserializer) (medium, CVSS 6.8, published 16 Jun 2026) - [CVE-2026-45134: LangChain LangSmith SDK untrusted deserialization in prompt pull methods](https://junglewise.ai/threats/cve-2026-45134-langchain-langsmith-sdk-untrusted-deserialization-in-prompt-pull) (high, CVSS 7.1, published 27 May 2026) - [CVE-2026-41488: LangChain langchain-openai SSRF bypass via DNS rebinding in _url_to_size](https://junglewise.ai/threats/cve-2026-41488-langchain-langchain-openai-ssrf-bypass-via-dns-rebinding-in-url) (low, CVSS 3.1, published 24 Apr 2026) - [CVE-2026-41481: LangChain langchain-text-splitters SSRF redirect bypass in HTMLHeaderTextSplitter](https://junglewise.ai/threats/cve-2026-41481-langchain-langchain-text-splitters-ssrf-redirect-bypass-in) (medium, CVSS 6.5, published 24 Apr 2026) - [CVE-2026-41182: LangChain LangSmith SDK sensitive information leak in streaming events](https://junglewise.ai/threats/cve-2026-41182-langchain-langsmith-sdk-sensitive-information-leak-in-streaming) (medium, CVSS 5.3, published 23 Apr 2026) - [CVE-2026-40087: LangChain incomplete f-string validation in prompt templates](https://junglewise.ai/threats/cve-2026-40087-langchain-incomplete-f-string-validation-in-prompt-templates) (medium, CVSS 5.3, published 9 Apr 2026) - [CVE-2026-27022: LangChain RediSearch query injection in langgraph-checkpoint-redis](https://junglewise.ai/threats/cve-2026-27022-langchain-redisearch-query-injection-in-langgraph-checkpoint) (low, CVSS 3.1, published 18 Feb 2026) - [CVE-2025-68665: LangChain serialization injection enables secret extraction](https://junglewise.ai/threats/cve-2025-68665-langchain-serialization-injection-enables-secret-extraction) (high, CVSS 8.6, published 23 Dec 2025) - [CVE-2025-68664: LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs](https://junglewise.ai/threats/cve-2025-68664-langchain-serialization-injection-vulnerability-enables-secret) (critical, CVSS 9.3, published 23 Dec 2025) - [CVE-2025-67644: PYSEC-2026-1530 - LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list…](https://junglewise.ai/threats/cve-2025-67644-langgraph-s-sqlite-is-vulnerable-to-sql-injection-via-metadata) (high, CVSS 7.3, published 11 Dec 2025) ## Most severe LangChain vulnerabilities - [CVE-2025-68664: LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs](https://junglewise.ai/threats/cve-2025-68664-langchain-serialization-injection-vulnerability-enables-secret) (critical, CVSS 9.3, published 23 Dec 2025) - [CVE-2025-68665: LangChain serialization injection enables secret extraction](https://junglewise.ai/threats/cve-2025-68665-langchain-serialization-injection-enables-secret-extraction) (high, CVSS 8.6, published 23 Dec 2025) - [CVE-2026-55253: LangChain MongoDB NoSQL injection in list/search methods](https://junglewise.ai/threats/cve-2026-55253-langchain-mongodb-nosql-injection-in-list-search-methods) (high, CVSS 7.7, published 14 Sep 2026) - [CVE-2025-67644: PYSEC-2026-1530 - LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list…](https://junglewise.ai/threats/cve-2025-67644-langgraph-s-sqlite-is-vulnerable-to-sql-injection-via-metadata) (high, CVSS 7.3, published 11 Dec 2025) - [CVE-2026-45134: LangChain LangSmith SDK untrusted deserialization in prompt pull methods](https://junglewise.ai/threats/cve-2026-45134-langchain-langsmith-sdk-untrusted-deserialization-in-prompt-pull) (high, CVSS 7.1, published 27 May 2026) - [CVE-2026-118668: LangGraph API JavaScript custom authentication namespace bypass](https://junglewise.ai/threats/cve-2026-118668-langgraph-api-implements-the-langgraph-api-for-rapid-development) (high, CVSS 4, published 28 Oct 2026) - [CVE-2026-104873: LangChain LangGraph Python SDK resource authorization bypass](https://junglewise.ai/threats/cve-2026-104873-langgraph-python-sdk-is-used-to-connect-to-running-langgraph-api) (high, CVSS 4, published 2 Oct 2026) - [CVE-2026-48775: LangChain LangGraph unsafe deserialization in JsonPlusSerializer](https://junglewise.ai/threats/cve-2026-48775-langchain-langgraph-unsafe-deserialization-in-jsonplusserializer) (medium, CVSS 6.8, published 16 Jun 2026) - [CVE-2026-48121: LangChain LangGraph NoSQL injection in MongoDBSaver](https://junglewise.ai/threats/cve-2026-48121-langchain-langgraph-nosql-injection-in-mongodbsaver) (medium, CVSS 6.7, published 4 Aug 2026) - [CVE-2026-41481: LangChain langchain-text-splitters SSRF redirect bypass in HTMLHeaderTextSplitter](https://junglewise.ai/threats/cve-2026-41481-langchain-langchain-text-splitters-ssrf-redirect-bypass-in) (medium, CVSS 6.5, published 24 Apr 2026) ## Vulnerabilities per week 4 vulnerabilities in the last four weeks, up 33% on the four before (3). | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 0 | 0 | 0 | | 31 Aug 2026 | 0 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 1 | 0 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 1 | 0 | 0 | | 5 Oct 2026 | 1 | 0 | 0 | | 12 Oct 2026 | 0 | 0 | 0 | | 19 Oct 2026 | 2 | 0 | 0 | | 26 Oct 2026 | 2 | 0 | 0 | | 2 Nov 2026 | 0 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## LangChain technologies - [LangChain LangSmith SDK](https://junglewise.ai/threats/technologies/langsmith-sdk): 4 vulnerabilities - [Langchain Core](https://junglewise.ai/threats/technologies/langchain-langchain-core): 3 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "LangChain vulnerabilities", https://junglewise.ai/threats/vendors/langchain, 9 November 2026.