langchain-core
Affected
- introduced
0.1.17, fixed0.1.53(ecosystem)
Fixed versions
0.1.53
Fix
- Fixed version
0.1.53pip install --upgrade langchain-core==0.1.53
Advisory
Also known as: CVE-2024-10940, PYSEC-2026-1517
langchain-core allows unauthorized users to read arbitrary files from the host file system
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.
Medium Basis: The source's own band: MODERATE
0.1.17, fixed 0.1.53 (ecosystem)0.1.53
0.1.53pip install --upgrade langchain-core==0.1.530.2.0, fixed 0.2.43 (ecosystem)0.2.43
0.2.43pip install --upgrade langchain-core==0.2.430.3.0, fixed 0.3.15 (ecosystem)0.3.15
0.3.15pip install --upgrade langchain-core==0.3.15Fix 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: GitHub Advisory Database (reviewed advisories) · CC BY 4.0