p PatchFirst

CVE-2026-105799

CVE-2026-105799 · LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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.

CVSS 2.3 · Low · EPSS 0.3% · Fix available

Published
Updated

Stack: node · database

Affected products and versions

  • langchainjs

    Versions
    • < 1.1.1: Affected

    No fix published

  • redis

    Versions
    • < 1.1.1: Affected

    No fix published

  • @langchain/redis npm

    Affected ranges
    • SEMVER: < 1.1.1

    Update to 1.1.1

Original sources

Check your server →