NVIDIA Triton Inference Server <= 26.02 - Authentication Bypass

NVIDIA Triton Inference Server contains an authentication bypass vulnerability, letting attackers bypass authentication and potentially execute code, escalate privileges, tamper data, cause denial of service, or disclose information, exploit requires no special conditions. id: CVE-2026-24207 info...

Triton

Triton is a dynamic binary analysis library. It provides internal components that allow you to build your program analysis tools, automate reverse engineering, perform software verification or just emulate code. Dynamic symbolic execution Dynamic taint analysis AST representation of the x86 ,...

exrop

Exrop Automatic ROP chain generator for x86-64 binaries, powered by Triton symbolic execution. Features Set registers to constants or other registers rdi=0x41414141, rdi=rax Write to memory constant and register-based addresses/values Write strings/bytes to memory Function calls with mixed...

triton-cve-2025-23320

Demonstrating CVE-2025-23320 This repo replicates CVE-2025-23320, demonstrating CWE-209, Generation of Error Message Containing Sensitive InformationCVSS Score: 7.5. This vulnerability exists on all NVIDIA Triton inference servers 25.06 and before. This docker setup runs a network containing an...

CVE-2026-47630

CVE-2026-47630 — NVIDIA Triton Inference Server: arbitrary dlopen via TRITONBATCHSTRATEGYPATH Absolute path traversal in the custom batching-strategy loader of triton-inference-server/core. A model configuration parameter is passed unvalidated to dlopenRTLDNOW | RTLDLOCAL, so anyone able to...

cve-2026-47627

CVE-2026-47627 — NVIDIA Triton Inference Server Path Traversal → DoS Zip-Slip Complete research writeup & PoC in this repo image nvcr.io/nvidia/tritonserver:26.05-py3 / server v2.69.0. Repo is set up to always be explicit so PoC works without restart via gRPC. Table of Contents 1. CVE Summary 2...

CVE-2026-24207

CVE-2026-24207 — NVIDIA Triton SageMaker Auth Bypass to Unauth RCE Unauthenticated attackers can reach the model-management surface of NVIDIA Triton Inference Server on the SageMaker and Vertex AI HTTP ports — bypassing the operator's --http-restricted-api configuration. Combined with the SageMak...

qsynthesis

Qsynthesis QSynthesis is a Python3 API to perform I/O based program synthesis of bitvector expressions. It aims at facilitating code deobfuscation. The algorithm is greybox approach combining both a blackbox I/O based synthesis and a whitebox AST search to synthesize sub-expressions if the root...

exrop

Exrop Generador automático de cadenas ROP para binarios x86-64, impulsado por la ejecución simbólica de Triton. Características Establecer registros a constantes u otros registros rdi=0x41414141, rdi=rax Escribir en memoria direcciones/valores basados en constantes y registros Escribir...

NVIDIA Triton Inference Server Auth Bypass (CVE-2026-24207)

Exploits CVE-2026-24207 in NVIDIA Triton Inference Server = 26.02: unauthenticated access to restricted HTTP APIs including /models and model management endpoints. !/usr/bin/env python3 -- coding: utf-8 -- """NVIDIA Triton Inference Server auth bypass CVE-2026-24207.""" import json from kittysplo...

CVE-2026-93841

A flaw was found in vLLM. This memory corruption vulnerability exists in the Triton bincountkernel, where prompt token identifiers IDs are used to index a bitset without proper bounds checking against the vocabulary size. A remote attacker can exploit this by submitting multimodal audio requests...

SUSE CVE-2026-93841

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton bincountkernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing...

Out-of-bounds Write

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Out-of-bounds Write via the Triton bincountkernel, where prompt token IDs index the penalty prompt-presence bitset without bounds checking against t...

PYSEC-2026-3999

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton bincountkernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing...

PYSEC-2026-3999

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton bincountkernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing...

PYSEC-0000-CVE-2026-93841

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton bincountkernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing...

CVE-2026-93841

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton bincountkernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing...

CVE-2026-93841

vLLM through 0.29.0 has a memory corruption vulnerability in the Triton _bincount_kernel used by the GPU sampler. Prompt token IDs index the penalty prompt-presence bitset without bounds checking against the vocabulary size. An unauthenticated attacker can submit multimodal audio requests contain...

Malicious Package

Overview lint-staged-mutation-orbit-triton is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and...

CVE-2026-93841: Improper Validation of Array Index

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton bincountkernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing...