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.
describes (1)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2026-34070US | — | Exploit | ||
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 embed… | ||||
references
External citations — patches, advisories, analysis.
- https://access.redhat.com/errata/RHSA-2026:24766ADVISORY
- https://access.redhat.com/errata/RHSA-2026:37275ADVISORY
- https://access.redhat.com/security/cve/CVE-2026-34070WEB
- https://bugzilla.redhat.com/show_bug.cgi?id=2453287REPORT
- https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47cFIX
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22ADVISORY
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54EVIDENCE
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34070.jsonWEB
Advisories like this name the exposed products attackers go after on your perimeter. See what is exposed on your perimeter with a free passive scan.
Free scan