langchain-core
Affected
- introduced
0, fixed1.2.22(ecosystem)
Fixed versions
1.2.22
Fix
- Fixed version
1.2.22pip install --upgrade langchain-core==1.2.22
Advisory
Also known as: CVE-2026-34070, GHSA-qh6h-p6c9-ff54
The record has no 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 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.
High Basis: CVSS v3 score 7.5, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
0, fixed 1.2.22 (ecosystem)1.2.22
1.2.22pip install --upgrade langchain-core==1.2.22Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0