# CVE-2025-33238: Race condition in Triton Inference Server

> An attacker can cause a denial of service in NVIDIA Triton Inference Server via a race condition in the Sagemaker HTTP server.

- **Severity:** High 7.5 (`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** Yes
- **Published:** 24 Mar 2026
- **Updated:** 25 Mar 2026
- **Also known as:** GHSA-5pqx-p8mp-cxrf, MINI-44fv-w77r-2pwh

## What is CVE-2025-33238?

CVE-2025-33238 is a high-severity vulnerability in Nvidia Triton Inference Server, published on 24 Mar 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official description

NVIDIA Triton Inference Server Sagemaker HTTP server contains a vulnerability where an attacker may cause an exception. A successful exploit of this vulnerability may lead to denial of service.

Weakness: CWE-362 (Concurrent Execution using Shared Resource with Improper Synchronization)

## Which versions are affected by CVE-2025-33238?

It affects 1 product.


Products: Nvidia Triton Inference Server.

## How do I fix CVE-2025-33238?

Apply the vendor's patch.

## Is CVE-2025-33238 being exploited?

There is no known exploitation of CVE-2025-33238 in the wild and no public exploit code.

## Other vulnerabilities in Nvidia Triton Inference Server

- [CVE-2026-47627](https://insights.sbomify.com/CVE-2026-47627/): Path traversal in Triton Inference Server (critical 9.8)
- [CVE-2026-24207](https://insights.sbomify.com/CVE-2026-24207/): Auth bypass in Triton Inference Server (critical 9.8)
- [CVE-2025-23316](https://insights.sbomify.com/CVE-2025-23316/): Command injection in Triton Inference Server (critical 9.8)
- [CVE-2025-23310](https://insights.sbomify.com/CVE-2025-23310/): Memory corruption in Triton Inference Server (critical 9.8)
- [CVE-2025-23311](https://insights.sbomify.com/CVE-2025-23311/): Memory corruption in Triton Inference Server (critical 9.8)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2025-33238 and fix it if it is affected.

What it is: CVE-2025-33238 is a high-severity vulnerability in Nvidia Triton Inference Server, published on 24 Mar 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: There is no known exploitation of CVE-2025-33238 in the wild and no public exploit code.

Affected product: Nvidia Triton Inference Server. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2025-33238/ (Markdown: https://insights.sbomify.com/CVE-2025-33238/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2025-33238
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2025-33238
- OSV: https://osv.dev/vulnerability/CVE-2025-33238

---
From sbomify Insights: https://insights.sbomify.com/CVE-2025-33238/
Summaries are generated and may contain mistakes; the official description above is the record.