---
title: "CVE-2023-43654: TorchServe Server-Side Request Forgery vulnerability"
url: https://erroneo.us/security/cve/CVE-2023-43654/
description: "CVE-2023-43654 (torchserve (PyPI)): TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper…"
type: vulnerability-record
section: "Security Digest"
date_published: 2023-09-28
date_modified: 2025-02-13
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2023-43654"
kev: false
cvss: 10
epss: 0.42495
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2023-43654: TorchServe Server-Side Request Forgery vulnerability

**Signal:** High exploit likelihood. EPSS ranks it in the top 5% of all CVEs for likely exploitation in the next 30 days. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 42.5% , percentile 99: FIRST’s model estimates a 42.5% chance of exploitation activity in the next 30 days, higher than 99% of all scored CVEs (very high). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes torchserve (PyPI) >= 0.1.0, < 0.8.2, fixed in 0.8.2 . Check your lockfile, including transitive dependencies.

## What it is

TorchServe is a tool for serving and scaling PyTorch models in production. TorchServe default configuration lacks proper input validation, enabling third parties to invoke remote HTTP download requests and write files to the disk. This issue could be taken advantage of to compromise the integrity of the system and sensitive data. This issue is present in versions 0.1.0 to 0.8.1. A user is able to load the model of their choice from any URL that they would like to use. The user of TorchServe is responsible for configuring both the allowedurls and specifying the model URL to be used. A pull request to warn the user when the default value for allowedurls is used has been merged in PR #2534. TorchServe release 0.8.2 includes this change. Users are advised to upgrade. There are no known workarounds for this issue.

## Affected packages

- PyPI `torchserve` >= 0.1.0, < 0.8.2 → fixed: 0.8.2

## Affected products (CVE record)

- pytorch serve: >= 0.1.0, < 0.8.2

## Severity

- GitHub_M CVSS 3.1: 10 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`
- GitHub CVSS 3.1: 9.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 42.49% probability of exploitation activity in the next 30 days; percentile 99.

## Sources

- [GitHub Advisory GHSA-8fxr-qfr9-p34w](https://github.com/advisories/GHSA-8fxr-qfr9-p34w)
- [CVE.org record CVE-2023-43654](https://www.cve.org/CVERecord?id=CVE-2023-43654)
- [NVD entry CVE-2023-43654](https://nvd.nist.gov/vuln/detail/CVE-2023-43654)
- [github.com](https://github.com/pytorch/serve/security/advisories/GHSA-8fxr-qfr9-p34w)
- [github.com](https://github.com/pytorch/serve/pull/2534)
- [github.com](https://github.com/pytorch/serve/releases/tag/v0.8.2)
- [packetstormsecurity.com](http://packetstormsecurity.com/files/175095/PyTorch-Model-Server-Registration-Deserialization-Remote-Code-Execution.html)

---
Source page: https://erroneo.us/security/cve/CVE-2023-43654/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt