Langchain-ai vulnerabilities
55 CVEs and advisories name Langchain-ai as an affected vendor, newest first. Follow it as a feed.
- CVE-2026-118668LangGraph JavaScript custom authentication may permit cross-user Store access
- CVE-2026-118667LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requests
- CVE-2026-115885LangGraph CLI prints the registry push token in `langgraph deploy --verbose` output
- CVE-2026-115883LangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite stores
- CVE-2026-106119LangChain: MongoDBChatMessageHistory query injection can allow cross-session access
- CVE-2026-105799LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values
- CVE-2026-104873LangGraph SDK custom auth silently ignores actions= on resource decorators
- CVE-2026-55253LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure
- CVE-2026-55235langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication
- CVE-2026-55236langgraph-api: Incomplete assistant authorization in LangGraph Server run creation
- CVE-2026-72848langchain-community SitemapLoader Does Not Apply restrict_to_same_domain to Nested Sitemap Index Entries, Allowing Server-Side Request Forgery
- CVE-2026-71433LangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite stores
- CVE-2026-48121@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access
- CVE-2026-59152Arbitrary server-side file read in LangSmith SDK TracingMiddleware
- CVE-2026-14742langchain-ai langgraph Task Result Cache _cache.py _freeze weak hash
- CVE-2026-55443LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders
- CVE-2026-48776LangGraph SDK has unsafe URL path construction
- CVE-2026-48775LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading
- CVE-2026-45134LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
- CVE-2026-44843LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists
- CVE-2026-41488angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding
- CVE-2026-41481LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypass
- CVE-2026-41182LangSmith SDK: Streaming token events bypass output redaction
- CVE-2026-40190LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash `set()`
- CVE-2026-40087LangChain has incomplete f-string validation in prompt templates
- CVE-2026-34070LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions
- CVE-2026-28277LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading
- CVE-2026-25750LangSmith Studio has URL Parameter Injection Vulnerability that Enables Token Theft via Malicious baseUrl
- CVE-2026-27795LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader
- CVE-2026-27794LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution