CVE-2023-31036
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.85%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering.
- CVSS 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.85% probability · 56th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-23, CWE-22
- Affected
- nvidia/triton inference server
- Source
- psirt@nvidia.com
References
- https://nvidia.custhelp.com/app/answers/detail/a_id/5509Vendor Advisory
- https://nvidia.custhelp.com/app/answers/detail/a_id/5509Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.