CVEs we hold for Langchain-ai

Records whose assigning authority named Langchain-ai as the affected vendor. Newest identifiers first, capped at 200.

CVE-2026-72848langchain-community SitemapLoader Does Not Apply restrict_to_same_domain to Nested Sitemap Index Entries, Allowing…langchain-ai langchain-community

CVE-2026-71433LangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite storeslangchain-ai langgraph-checkpoint-postgres

CVE-2026-59152Arbitrary server-side file read in LangSmith SDK TracingMiddlewarelangchain-ai langsmith-sdk

CVE-2026-55443LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaderslangchain-ai langchain-anthropic

CVE-2026-55253LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposurelangchain-ai langgraph-store-mongodb

CVE-2026-55236langgraph-api: Incomplete assistant authorization in LangGraph Server run creationlangchain-ai langgraph-api

CVE-2026-55235langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authenticationlangchain-ai langgraph-api

CVE-2026-48776LangGraph SDK has unsafe URL path constructionlangchain-ai; langchain-ai langchain-sdk

CVE-2026-48775LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loadinglangchain-ai langraph-checkpoint

CVE-2026-48121@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state accesslangchain-ai langgraphjs

CVE-2026-45134LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warninglangchain-ai langsmith-sdk

CVE-2026-44843LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlistslangchain-ai langchain

CVE-2026-41488angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebindinglangchain-ai langchain-openai

CVE-2026-41481LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypasslangchain-ai langchain-text-splitters

CVE-2026-41182LangSmith SDK: Streaming token events bypass output redactionlangchain-ai langsmith-sdk

CVE-2026-40190LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash…langchain-ai langsmith-sdk

CVE-2026-40087LangChain has incomplete f-string validation in prompt templateslangchain-ai langchain

CVE-2026-34070LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functionslangchain-ai langchain

CVE-2026-28277LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loadinglangchain-ai langgraph

CVE-2026-27795LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoaderlangchain-ai langchainjs

CVE-2026-27794LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Executionlangchain-ai langgraph-checkpoint

CVE-2026-27022RediSearch Query Injection in @langchain/langgraph-checkpoint-redislangchain-ai langgraphjs

CVE-2026-26019@langchain/community affected by SSRF Bypass in RecursiveUrlLoader via insufficient URL origin validationlangchain-ai langchainjs

CVE-2026-26013LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messageslangchain-ai langchain

CVE-2026-25750LangSmith Studio has URL Parameter Injection Vulnerability that Enables Token Theft via Malicious baseUrllangchain-ai helm

CVE-2026-25528LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injectionlangchain-ai langsmith-sdk

CVE-2026-14742langchain-ai langgraph Task Result Cache _cache.py _freeze weak hashlangchain-ai langgraph

CVE-2025-8709SQL Injection in langchain-ai/langchainlangchain-ai/langchain

CVE-2025-6985XXE Vulnerability in langchain-ai/langchainlangchain-ai/langchain

CVE-2025-6984Sensitive Information Disclosure Due to Insecure XML Parsing in langchain-ai/langchainlangchain-ai/langchain

CVE-2025-68665LangChain serialization injection vulnerability enables secret extractionlangchain-ai langchainjs

CVE-2025-68664LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIslangchain-ai langchain

CVE-2025-67644LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list methodlangchain-ai langgraph

CVE-2025-65106LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templateslangchain-ai langchain

CVE-2025-64439LangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializerlangchain-ai langgraph

CVE-2025-64104LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStorelangchain-ai langgraph

CVE-2025-2828SSRF Vulnerability in RequestsToolkit in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-8309SQL Injection in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-7774Path Traversal in langchain-ai/langchainjslangchain-ai/langchainjs

CVE-2024-7042Prompt Injection in langchain-ai/langchainjs Leading to SQL Injectionlangchain-ai/langchainjs

CVE-2024-5998Deserialization of Untrusted Data in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-3571Path Traversal in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-3095SSRF in Langchain Web Research Retriever in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-2965Denial-of-Service in LangChain SitemapLoader in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-1455Billion Laughs Attack leading to DoS in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-10940Exposure of Sensitive System Information via ImagePromptTemplate in langchain-ai/langchainlangchain-ai/langchain

CVE-2024-0243Server-side Request Forgery In Recursive URL Loaderlangchain-ai/langchain

47 records, read from the index as it stood on 20 Sep 2026. Every row opens the record it names, and every value on that record opens its own receipt.

Everything on this page is free. Public data. Withholding it protects nothing.