CVE-2026-47472
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 TensorRT-LLM contains a vulnerability in its inter-process communication layer where an attacker with local same-user access could cause deserialization. A successful exploit of this vulnerability might lead to code execution, information disclosure, data tampering, and 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 TensorRT-LLM contains a deserialization vulnerability in its inter-process communication (IPC) layer. An attacker with local access to the same user account can exploit the insecure IPC channel to deserialize malicious data, potentially achieving code execution, leaking sensitive information, tampering with data, or causing denial of service.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS 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
- Local
- Complexity
- Low
- Privileges
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:L/AC:L/PR:L/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 TensorRT-LLM is installedRun command: pip show tensorrt-llm or check for tensorrt_llm Python package; alternatively, search for /usr/local/tensorrt_llm or /opt/nvidia/tensorrt_llm directoriesAffected if TensorRT-LLM is present on the system
-
Determine the installed TensorRT-LLM versionRun: pip show tensorrt-llm | grep Version, or import tensorrt_llm and print(tensorrt_llm.__version__)Affected if The installed version has not received the CVE-2026-47472 patch (compare against any official NVIDIA advisory version)
-
Verify if IPC functionality is enabledCheck TensorRT-LLM configuration files (e.g., in the working directory or /etc/tensorrt_llm/) for settings related to ipc_enabled, ipc_channel, or inter_process_communication; also inspect any launcher scripts for --ipc or --use_ipc flagsAffected if IPC is explicitly enabled or defaults to enabled in the configuration
-
Inspect active IPC channels and socketsList temporary/shared memory regions: ls -la /dev/shm/ and check for tensorrt_llm IPC socket files; run: ps aux | grep tensorrt_llm to see running processes and their IPC endpointsAffected if IPC sockets or shared memory files owned by the tensorrt_llm process are present and accessible to other local users in the same account group
-
Check user isolation and access controlsReview file permissions on IPC-related directories: ls -la /tmp/tensorrt_llm* and /dev/shm/*tensorrt*; verify which users have access to these IPC channelsAffected if Other local users in the same account can read/write to the IPC channels (permissions are overly permissive, e.g., 777 or shared group)
If TensorRT-LLM is installed with IPC functionality enabled and other local users can access the IPC channels, the environment is vulnerable to CVE-2026-47472.
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.
From vendor dataApply the NVIDIA TensorRT-LLM security patch when available. Until then, restrict local access to the system, apply least-privilege principles to user accounts running TensorRT-LLM, and consider network isolation if the IPC layer has any network exposure.
- Consultation3.0 h
- Implementation6.0 h
- Testing3.0 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 $3,984.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-47472 — 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-2026-47472 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