CVE-2026-24233
published 2026-07-14CVE-2026-24233: NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated…
PriorityP347high8.4CVSS 3.1
AVLACLPRNUINSUCHIHAH
EPSS
0.39%
31.9th percentile
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, data tampering, and information disclosure.
Affected
1 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| nvidia | tensorrt-llm | 0.0 – v1.3.0 rc14 | — |
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
VulDB
NVIDIA TensorRT-LLM up to 1.3.0 rc14 Model Weight Deserializer deserialization
vuldb·2026-07-15·CVSS 8.4
CVE-2026-24233 [HIGH] NVIDIA TensorRT-LLM up to 1.3.0 rc14 Model Weight Deserializer deserialization
A vulnerability was found in NVIDIA TensorRT-LLM up to 1.3.0 rc14. It has been rated as very critical. Affected by this issue is some unknown functionality of the component Model Weight Deserializer. The manipulation leads to deserialization.
This vulnerability is uniquely identified as CVE-2026-24233. Local access is required to approach this attack. No exploit exists.
GHSA
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrust
ghsa_unreviewed·2026-07-14
CVE-2026-24233 [HIGH] CWE-502 NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrust
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, data tampering, and information disclosure.
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2026-07-14
Published