---
id: CVE-2024-35199
aliases:
  - GHSA-hhpg-v63p-wp7w
  - PYSEC-2026-1971
title: TorchServe gRPC Port Exposure
summary: TorchServe gRPC Port Exposure
severity: high
cvss: 8.2
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H'
vendor: torchserve
product: torchserve
ecosystem: pip
affected:
  - 'torchserve >= 0.3.0, < 0.11.0'
patched:
  - torchserve 0.11.0
published: '2024-07-18'
updated: '2026-09-10'
sourceUpdated: '2026-09-10T03:50:16.759094781Z'
source: OSV
sourceUrl: 'https://osv.dev/vulnerability/GHSA-hhpg-v63p-wp7w'
references:
  - url: 'https://github.com/pytorch/serve/security/advisories/GHSA-hhpg-v63p-wp7w'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2024-35199'
  - url: 'https://github.com/pytorch/serve/pull/3083'
  - url: >-
      https://github.com/pytorch/serve/commit/aab99506a17193de217aacc1119d9381dbc6ed2b
  - url: 'https://github.com/pytorch/serve'
  - url: 'https://github.com/pytorch/serve/releases/tag/v0.11.0'
tags:
  - osv
  - pip
epss: 0.00637
epssPercentile: 0.49151
ingestedAt: '2026-07-08T18:25:50.242Z'
---

## Overview

### Impact
The two gRPC ports 7070 and 7071, are not bound to [localhost](http://localhost/) by default, so when TorchServe is launched, these two interfaces are bound to all interfaces. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected.

### Patches
This issue in TorchServe has been fixed in [#3083](https://github.com/pytorch/serve/pull/3083).

TorchServe release 0.11.0 includes the fix to address this vulnerability.

### References
* [#3083](https://github.com/pytorch/serve/pull/3083)
* [TorchServe release v0.11.0](https://github.com/pytorch/serve/releases/tag/v0.11.0)

Thank Kroll Cyber Risk for for responsibly disclosing this issue.

If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [aws-security@amazon.com](mailto:aws-security@amazon.com). Please do not create a public GitHub issue.

## Affected packages

- `torchserve >= 0.3.0, < 0.11.0`

## Remediation

Upgrade to a patched release:

- `torchserve 0.11.0`