CVE-2025-23317: NVIDIA Triton Inference Server contains a vulnerability in the HTTP server, where an attacker could start a reverse shel
Summary
NVIDIA Triton Inference Server has a vulnerability in its HTTP server (CVE-2025-23317) where an attacker could send a specially crafted HTTP request to start a reverse shell (a remote connection giving the attacker control of the system). This could allow remote code execution (running commands on a system without permission), denial of service (making the system unavailable), data tampering, or information disclosure.
Vulnerability Details
9.1(critical)
EPSS: 2.8%
Classification
Affected Vendors
Related Issues
CVE-2022-29200: TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, the implem
CVE-2022-21727: Tensorflow is an Open Source Machine Learning Framework. The implementation of shape inference for `Dequantize` is vulne
Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-23317
First tracked: February 15, 2026 at 08:45 PM
Classified by LLM (prompt v3) · confidence: 95%