LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values

[ Description ]Official description

LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alter or broaden the generated search query. When an application uses an attacker-influenceable filter as a tenant or document-access boundary, the modified query can expose indexed documents outside the attacker's intended scope. This issue is fixed in version 1.1.1.

[ Fixes ]Fixes and patches

• @langchain/redis 1.1.1Fixed version · GitHub Advisories · npm package @langchain/redis: upgrade to 1.1.1 or later (affected <= 1.1.0)

[ Advisories ]Government CERT advisories

• BSI CERT-Bund6 Oct 2026WID-SEC-2026-3776

  LangChain: Multiple vulnerabilities Translated from German

  CVE-2026-106119CVE-2026-105799

[ Packages ]Affected open-source packages

• @langchain/redis npmAffected <= 1.1.0 · fixed in 1.1.1 · GHSA-5x6v-p487-7qh2

[ References ]References

• github.com/langchain-ai/langchainjs/commit/880e3969ea643a2147777a4d5e8bd606a697edf7
• github.com/langchain-ai/langchainjs/pull/10701
• github.com/langchain-ai/langchainjs/releases/tag/@langchain/redis@1.1.1
• github.com/langchain-ai/langchainjs/security/advisories/GHSA-5x6v-p487-7qh2