Description
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
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| langchain-ai | langchain | < 1.2.22 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
GitHub 1 repository
-
Rickidevs/CVE-2026-34070 ★ 0 · Mar 26, 2026
I Found a Zero-Day Vulnerability in langchain — Here’s How It Went
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | langchain-core | < 1.2.22 | 1.2.22 | GHSA-qh6h-p6c9-ff54 |
Advisories 1
- WID-SEC-2026-0896 LangChain: Schwachstelle ermöglicht Offenlegung von Informationen BSI CERT-Bund (WID) · Jul 9, 2026