Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
CRITICAL severity

GHSA-wxcx-gg9c-fwp2 — torchserve

CRITICALFix: pytorch/serve#3082

GHSA-wxcx-gg9c-fwp2 is a critical-severity (CVSS 9.8) CWE-706 vulnerability in torchserve. A fix is available for torchserve — see the affected versions and patch details below.

TorchServe vulnerable to bypass of allowed_urls configuration

Also known asCVE-2024-35198PYSEC-2026-554
Published
Jul 18, 2024
Updated
Sep 10, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 26, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for GHSA-wxcx-gg9c-fwp2.

EPSS Exploitation Probability

via FIRST.org ↗
0.8%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs55th percentile — riskier than 55% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

GHSA-wxcx-gg9c-fwp2 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.

Where this sits among everything scored

Of 379,842 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.

Real-World Exposure

1 pkg affected
🐍torchserve

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Impact

TorchServe's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected.

Patches

This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading: #3082.

TorchServe release 0.11.0 includes the fix to address this vulnerability.

References

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 or directly via email to [email protected]. Please do not create a public GitHub issue.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPItorchserveall versions0.11.0pip install --upgrade 'torchserve==0.11.0'

Affected Products

1 product · 1 configurations
Application
torchservepytorch
≥ 0.4.2 && < 0.11.0
range

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for torchserve, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update torchserve to 0.11.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-wxcx-gg9c-fwp2 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Frequently Asked Questions

### Impact TorchServe's check on allowed_urls configuration can be by-passed if the URL contains characters such as ".." but it does not prevent the model from being downloaded into the model store. Once a file is downloaded, it can be referenced without providing a URL the second time, which effectively bypasses the allowed_urls security check. Customers using PyTorch inference Deep Learning Containers (DLC) through Amazon SageMaker and EKS are not affected. ### Patches This issue in TorchServe has been fixed by validating the URL without characters such as ".." before downloading: [#3082](h
O3 Security · Impact-Aware SCA

Is GHSA-wxcx-gg9c-fwp2 in your dependencies?

Find it across PyPI, including transitive dependencies.

GHSA-wxcx-gg9c-fwp2: torchserve | O3 Security