Local code execution via unsafe MPI deserialization
Published May 20, 2026 · Updated May 20, 2026
Unsafe deserialization in NVIDIA TensorRT-LLM before 1.2 allows local users with high privileges to execute code through the MPI server. The MPI server reconstructs attacker-controlled serialized data without safe deserialization controls; NVIDIA has not disclosed the specific function or data format. Exploitation requires high local privileges and difficult conditions, and successful attacks can also interrupt service, alter data, or disclose information.
Summary
What happened
Unsafe deserialization in NVIDIA TensorRT-LLM before 1.2 allows local users with high privileges to execute code through the MPI server. The MPI server reconstructs attacker-controlled serialized data without safe deserialization controls; NVIDIA has not disclosed the specific function or data format. Exploitation requires high local privileges and difficult conditions, and successful attacks can also interrupt service, alter data, or disclose information.
The record
- CVE
- CVE-2025-33255
- Published
- May 20, 2026
- Updated
- May 20, 2026
- Vendor
- DPDK Project
- Product
- TensorRT-LLM
- Classifications
- CWE-502
- Attack vector
- local
- Privileges
- admin
Timeline
How it unfolded
- May 20, 2026CVE publishedPublication date reported by the CVE source.
- May 20, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <v1.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo