{"id":"CVE-2026-105799","title":"LangChain is a framework for building LLM-powered applications","summary":"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 Re…","severity":"low","cvss":2.3,"cvssVector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N","cwe":["CWE-943"],"vendor":"langchain","product":"@langchain/redis","affected":["@langchain/redis <= 1.1.0"],"patched":["@langchain/redis 1.1.1"],"published":"2026-10-06","updated":"2026-10-06","sourceUpdated":"2026-10-06T15:19:48.933","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-105799","references":[{"url":"https://github.com/langchain-ai/langchainjs/commit/880e3969ea643a2147777a4d5e8bd606a697edf7","label":"security-advisories@github.com"},{"url":"https://github.com/langchain-ai/langchainjs/pull/10701","label":"security-advisories@github.com"},{"url":"https://github.com/langchain-ai/langchainjs/releases/tag/@langchain/redis@1.1.1","label":"security-advisories@github.com"},{"url":"https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-5x6v-p487-7qh2","label":"security-advisories@github.com"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-105799"},{"url":"https://github.com/advisories/GHSA-5x6v-p487-7qh2"}],"tags":["nvd","ghsa","npm","cve.org"],"aliases":["GHSA-5x6v-p487-7qh2"],"ecosystem":"npm","cvssSource":"cna","ingestedAt":"2026-10-06T15:01:49.302Z","slug":"CVE-2026-105799","body":"## Overview\n\nLangChain 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.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Package advisory (CVE-2026-105799)\n\nAffected packages:\n\n- `@langchain/redis <= 1.1.0`\n\nPatched in:\n\n- `@langchain/redis 1.1.1`\n\nSource: https://github.com/advisories/GHSA-5x6v-p487-7qh2","depth":"sunlit","depthScore":13,"depthScoreParts":{"impact":12.6,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}