CVE-2026-44223

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The extracthiddenstates speculative decoding proposer returns a tensor with an incorrect shape after the first decode step. This can be triggered by a remote attacker sending a request that uses sampling...

CVE-2026-47487

NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repository to be read, written to, or modified by providing a path in the model name to the Triton MLflow plugin. A successful exploit of this vulnerability might lead to denial of...

EUVD-2026-52799

NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repository to be read, written to, or modified by providing a path in the model name to the Triton MLflow plugin. A successful exploit of this vulnerability might lead to denial of...

Security Bulletin: NVIDIA Triton Inference Server - August 2026

NVIDIA has released a software update for NVIDIA® Triton Inference Server. To protect your system, clone or update this software to Triton Server r26.03 or later from the NVIDIA Triton Inference Server GitHub repo. Go to NVIDIA Product Security. Details The following table summarizes the potentia...

CVE-2026-45376 Decidim: Admin user search allows SQL injection through similarity-based sorting

Decidim is a participatory democracy framework. Prior to 0.30.9, from 0.31.0 before 0.31.5, and in 0.32.0.rc1 before 0.32.0.rc2, the GET /admin/organization/users search interpolates params:term into raw Arel.sql ORDER BY similarity expressions before sanitization, allowing an authenticated...

CVE-2026-45376 Decidim: Admin user search allows SQL injection through similarity-based sorting

Decidim is a participatory democracy framework. Prior to 0.30.9, from 0.31.0 before 0.31.5, and in 0.32.0.rc1 before 0.32.0.rc2, the GET /admin/organization/users search interpolates params:term into raw Arel.sql ORDER BY similarity expressions before sanitization, allowing an authenticated...

CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

CVE-2026-15971 CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

EUVD-2026-51262

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

CVE-2026-15971

SGLang contains a remote code execution vulnerability (CVE-2026-15971) that triggers when the optional dumper subsystem is enabled. The root cause is a sandbox escape via DUMPER_SERVER_PORT, enabling code execution on inference requests. Multiple sources (NVD, CVE lists, OSV, etc.) consistently d...

CVE-2026-15971 CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

PT-2026-66559

Name of the Vulnerable Software and Affected Versions SGLang affected versions not specified Description An issue exists when the optional dumper subsystem is enabled and the DUMPER SERVER PORT variable is set. This allows for a sandbox escape, which can lead to remote code execution during...

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

CVE-2026-56764

A flaw was found in Hono. This vulnerability, a timing attack, exists in the basicAuth and bearerAuth middlewares due to a non-constant-time string comparison. A remote attacker could exploit the early termination of string equality checks to infer valid credentials by precisely measuring respons...

CVE-2026-66005

CVE-2026-66005 affects Jan up to version 0.8.4. The local API server has a CORS misconfiguration that replaces user-configured trusted hosts with a wildcard, reflecting arbitrary origins with credentials. This enables network-adjacent attackers to bypass trusted host restrictions and reach the un...

PT-2026-64318

Jan through 0.8.4, fixed in commit 3e1c1e7, contains a CORS misconfiguration vulnerability in its local API server that allows network-adjacent attackers to bypass trusted host restrictions by exploiting the server's replacement of user-configured trusted hosts with a wildcard that reflects...

EUVD-2026-41925

vLLM denial of service via prompt embeds on M-RoPE models...

CVE-2026-63086

text-generation-inference through 3.3.7 contains a server-side request forgery SSRF vulnerability in the OpenAI-compatible multimodal chat completions endpoint that allows unauthenticated network attackers to coerce the server into issuing arbitrary HTTP GET requests by supplying a crafted imageu...

CVE-2026-63086

The CVE-2026-63086 entry concerns text-generation-inference 3.3.7, with an SSRF flaw in the OpenAI-compatible multimodal chat completions endpoint. The fetch_image function in router/src/validation.rs does not validate addresses (private, loopback, link-local, or cloud metadata). The HTTP client ...

CVE-2026-58658

GPUStack through 2.2.1, fixed in commit 4e20551, contains an unauthenticated information disclosure vulnerability that allows unauthenticated attackers to access sensitive inference logs and modify worker configuration by exploiting unprotected /serveLogs and /debug endpoints on the worker port...