GHSA-5chr-fjjv-38qv

langchain-core allows unauthorized users to read arbitrary files from the host file system

At a glance

Published
Updated
CVE
CVE-2024-10940
Aliases
PYSEC-2026-1517
CVSS_V3
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Description

A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchain_core.prompts.ImagePromptTemplate's (and by extension langchain_core.prompts.ChatPromptTemplate's) with input variables that can read any user-specified path from the server file system. If the outputs of these prompt templates are exposed to the user, either directly or through downstream model outputs, it can lead to the exposure of sensitive information.

Affected packages

PackageVersions
PyPI · langchain-coreintroduced 0.1.17, fixed 0.1.53
PyPI · langchain-coreintroduced 0.2.0, fixed 0.2.43
PyPI · langchain-coreintroduced 0.3.0, fixed 0.3.15

References

Sources

SourceLicence
OSV.devCC-BY 4.0 — GitHub Advisory Database