Local code execution via unsafe weight deserialization
Published Jul 14, 2026 · Updated Jul 14, 2026
Deserialization of untrusted data in NVIDIA TensorRT-LLM 1.3.0rc14 and earlier allows local users to execute code through model weights. The restricted unpickler processes attacker-controlled serialized model-weight data, but NVIDIA has not disclosed the offending method or exact unsafe object handling. Local access without authentication is required; successful exploitation grants code execution and can elevate privileges, alter data, or disclose information.
Summary
What happened
Deserialization of untrusted data in NVIDIA TensorRT-LLM 1.3.0rc14 and earlier allows local users to execute code through model weights. The restricted unpickler processes attacker-controlled serialized model-weight data, but NVIDIA has not disclosed the offending method or exact unsafe object handling. Local access without authentication is required; successful exploitation grants code execution and can elevate privileges, alter data, or disclose information.
The record
- CVE
- CVE-2026-24233
- Published
- Jul 14, 2026
- Updated
- Jul 14, 2026
- Vendor
- DPDK Project
- Product
- TensorRT-LLM
- Classifications
- CWE-502, T1068
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 14, 2026CVE publishedPublication date reported by the CVE source.
- Jul 14, 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=0.0 <=v1.3.0 rc14
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