{"id":"CVE-2026-34070","title":"LangChain is a framework for building agents and LLM-powered applications","summary":"LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating again…","severity":"high","cvss":7.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","cwe":["CWE-22"],"vendor":"langchain","product":"langchain_core","affected":["langchain_core < 1.2.22"],"patched":["langchain_core 1.2.22"],"published":"2026-03-31","updated":"2026-07-10","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-34070","references":[{"url":"https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c","label":"security-advisories@github.com"},{"url":"https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22","label":"security-advisories@github.com"},{"url":"https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54","label":"security-advisories@github.com"},{"url":"https://access.redhat.com/errata/RHSA-2026:24766","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:37275","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/security/cve/CVE-2026-34070","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2453287","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54","label":"134c704f-9b21-4f2e-91b3-4a467353bcc0"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34070.json","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-34070"},{"url":"https://github.com/langchain-ai/langchain"}],"tags":["nvd","exploit-available","osv","pip"],"epss":0.01382,"epssPercentile":0.70985,"ingestedAt":"2026-07-10T13:03:45.535Z","exploits":{"github":1,"githubRepos":["https://github.com/Rickidevs/CVE-2026-34070"],"checkedAt":"2026-09-24T07:53:02.540Z"},"exploitAvailable":true,"aliases":["GHSA-qh6h-p6c9-ff54","PYSEC-2026-2193"],"ecosystem":"pip","slug":"CVE-2026-34070","body":"## Overview\n\nLangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.\n\n## Affected\n\n- `langchain_core < 1.2.22`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `langchain_core 1.2.22`\n\n## Package advisory (CVE-2026-34070)\n\nAffected packages:\n\n- `langchain-core < 1.2.22`\n\nPatched in:\n\n- `langchain-core 1.2.22`\n\nSource: https://osv.dev/vulnerability/GHSA-qh6h-p6c9-ff54","depth":"midnight","depthScore":54,"depthScoreParts":{"impact":41.3,"likelihood":0.3,"exploitation":12,"ransomware":0},"changes":[{"seq":5121,"id":"CVE-2026-34070","ts":1788887248942,"field":"exploit_available","old":"false","new":"true"},{"seq":4004,"id":"CVE-2026-34070","ts":1788886364624,"field":"exploit_available","old":"true","new":"false"},{"seq":2816,"id":"CVE-2026-34070","ts":1788883031315,"field":"exploit_available","old":"false","new":"true"},{"seq":1845,"id":"CVE-2026-34070","ts":1788882434241,"field":"exploit_available","old":"true","new":"false"},{"seq":943,"id":"CVE-2026-34070","ts":1788881868264,"field":"exploit_available","old":"false","new":"true"}]}