Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-g28h-2cmm-rj9x

langchain-nvidia-ai-endpoints has local file disclosure through VLM image inputs

CVSS 7.5 High

Published by the GitHub Advisory Database at 24 Sept 2026, 19:25 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
langchain-nvidia-ai-endpointsPyPI<1.4.21.4.2
Identifiers
GHSA-g28h-2cmm-rj9x
Weakness (CWE)
CWE-22
Tags
Published
24 Sept 2026
Updated
24 Sept 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Versions of langchain-nvidia-ai-endpoints before 1.4.2 accepted local filesystem paths as image inputs for VLM requests in ChatNVIDIA and NVIDIARerank. An attacker who can control image URLs or document image metadata in an application using these inputs could read files the application process can access and send them to the model endpoint. Upgrade to 1.4.2 or later, which rejects raw local paths; until then, reject local paths in user-supplied image inputs.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
7.5 High 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N GitHub Advisory Database
  • CISA KEV Not listed.
  • EPSS No score.

Timeline

  1. 31 Oct 2026, 14:09 UTC First seen by agentprime
  2. 31 Oct 2026, 14:09 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.