NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-o…
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.
The product uses a sequential operation to read or write a buffer, but it uses an incorrect length value that causes it to access memory that is outside of the bounds of the buffer.
https://cwe.mitre.org/data/definitions/805.html →Open in CWE collection →Buffer Overflow attacks target improper or missing bounds checking on buffer operations, typically triggered by input injected by an adversary. As a consequence, an adversary is able to write past the boundaries of allocated buffer regions in memory, causing a program crash or potentially redirection of execution as per the adversaries' choice.
https://capec.mitre.org/data/definitions/100.html →Open in CAPEC collection →An attacker sends a SOAP request with an array whose actual length exceeds the length indicated in the request. If the server processing the transmission naively trusts the specified size, then an attacker can intentionally understate the size of the array, possibly resulting in a buffer overflow if the server attempts to read the entire data set into the memory it allocated for a smaller array.
https://capec.mitre.org/data/definitions/256.html →Open in CAPEC collection →| Product | Vendor | Status |
|---|---|---|
| Tracked | ||
| triton_inference_server | * | Tracked |