CVE-2025-23317
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 server, where an attacker could start a reverse shell by sending a specially crafted HTTP request. A successful exploit of this vulnerability might lead to remote code execution, denial of service, data tampering, or information disclosure.
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 critical vulnerability in its HTTP server component where specially crafted HTTP requests can trigger remote code execution, enabling attackers to establish reverse shells. The vulnerability is network-exploitable and of low complexity, requiring only standard HTTP requests to trigger the RCE vector.
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< 25.07CVSS 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
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/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 if Triton Inference Server is installedCheck for Triton Inference Server processes running on the system (e.g., 'ps aux | grep triton' or check for container named 'triton'), or look for installation directories typically used for NVIDIA softwareAffected if Triton Inference Server is present on the system
-
Determine the installed Triton Inference Server versionRun 'tritonserver --version' if the binary is available, check the Docker image tag if running in a container, or inspect the installation metadataAffected if The version is lower than 25.07 (e.g., 25.06, 25.05, older releases)
-
Verify the HTTP server component is enabledCheck Triton configuration for HTTP server settings (typically via config.pbtxt or command-line flags like '--http-server-port' or '--allow-http'), or verify the service is listening on HTTP ports (80, 8000, 8001)Affected if HTTP server is enabled and listening on any HTTP port
-
Assess network exposure of HTTP endpointsReview firewall rules, network ACLs, or Kubernetes network policies controlling access to Triton HTTP ports; check if ports are binded to 0.0.0.0 vs localhostAffected if HTTP endpoints are accessible from untrusted networks or the internet without proper access controls
The environment is affected if Triton Inference Server version is below 25.07 AND the HTTP server component is enabled and accessible from a network where attackers could send malicious HTTP requests.
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 · scoped25.07
Apply NVIDIA security patches when available; until then, restrict network access to Triton Inference Server HTTP endpoints, implement WAF rules for anomalous HTTP request patterns, and monitor for Indicators of Compromise.
Triton Inference Server 25.07 or later
- 1. Back up your current Triton Inference Server configuration and any custom models
- 2. Stop the currently running Triton Inference Server instance
- 3. Pull the fixed Triton Inference Server container image with tag 25.07 or later (e.g., nvcr.io/nvidia/tritonserver:25.07-py3)
- 4. Verify the image integrity using NVIDIA's provided checksums if available
- 5. Update your deployment configuration to use the new image version
- 6. Start the upgraded Triton Inference Server container
- 7. Verify the server is operational by checking health endpoints and running a test inference
- 8. Monitor logs for any unusual activity during the transition
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation4.0 h
- Implementation8.0 h
- Testing6.0 h
- Review / QA4.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,176.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2025-23317 — 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-2025-23317 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