CVE-2026-24158
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedNVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · moderate confidenceNVIDIA Triton Inference Server contains a denial of service vulnerability in its HTTP endpoint where an attacker can send a large compressed payload to exhaust server resources and cause service disruption.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 26.01CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- None
- Integrity
- None
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Identify Triton Inference Server versionRun 'tritonserver --version' or check the container image tag if running in Docker. If installed as a service, check the installed package version via your package manager.Affected if The installed version is lower than 26.01 (e.g., 25.x, 24.x series)
-
Confirm HTTP endpoint is enabledCheck the Triton server startup configuration or command-line arguments for '--http-port' or '--allow-http'. Review any nginx or reverse proxy configuration that forwards HTTP requests to Triton.Affected if HTTP endpoint is actively listening on any port (default 8000)
-
Inspect HTTP endpoint configuration for size limitsReview the Triton configuration file (config.pbtxt) or command-line flags for settings like 'http_max_payload_size', 'max_compressed_size', or similar limits on compressed request bodies.Affected if No explicit size limits are configured for compressed payloads, or limits are set to very high values (several hundred MB or unlimited)
-
Check for request timeout settingsLook for timeout-related configuration such as 'http_read_timeout' or 'request_timeout' in the config.pbtxt or server startup parameters.Affected if No HTTP request timeouts are configured, or timeouts are set very high
-
Review request logging and monitoringExamine Triton server logs and any monitoring tools (e.g., Prometheus metrics at /metrics endpoint) for logged request sizes or compression ratios.Affected if No logging or alerting exists for unusually large compressed requests
You are affected if running Triton Inference Server version below 26.01 with the HTTP endpoint enabled and without input size limits or timeouts configured for compressed payloads.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped26.01
Implement input size limits and timeouts for compressed payloads in the HTTP endpoint configuration, and monitor for anomalous large compressed requests.
26.01
- Verify current Triton Inference Server version using the server's metrics or logs
- Plan maintenance window for the upgrade as Triton will need to be restarted
- Stop the currently running Triton Inference Server instance
- Download Triton Inference Server version 26.01 or later from NVIDIA's official repository or container registry
- Install or deploy the new version following standard Triton deployment procedures
- Start the upgraded Triton Inference Server
- Verify the server is running correctly and HTTP endpoints are responding normally
- Monitor for any issues and review logs to confirm the vulnerability is mitigated
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation4.0 h
- Implementation8.0 h
- Testing6.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,600.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-24158 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-24158 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data