CVE-2026-34070
EUVD-2026-1728331.03.2026, 03:15
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.
Affected Products (NVD)
| Vendor | Product | Version |
|---|---|---|
| langchain | langchain_core | 𝑥 < 1.2.22 |
𝑥
= Vulnerable software versions
Early Detection
Affected products identified ahead of NVD analysis through intelligence sources.
| Vendor | Product | Version | Source |
|---|---|---|---|
| Red Hat | Red Hat Ansible Automation Platform 2.5 | 1780082949 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat OpenShift AI 3.3 | 1782471587 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat OpenShift AI 3.3 | 1782471606 ≤ 𝑥 < * | ADP |
References