Security Vulnerabilities
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
CVSS Score
7.5
EPSS Score
0.004
Published
2026-06-22
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.
CVSS Score
6.5
EPSS Score
0.001
Published
2026-06-22
vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.
CVSS Score
9.1
EPSS Score
0.007
Published
2026-06-22
vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.
CVSS Score
5.3
EPSS Score
0.003
Published
2026-06-22
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.
CVSS Score
8.8
EPSS Score
0.003
Published
2026-06-22
Nuxt versions 4.0.0 before 4.4.7 and 3.x before 3.21.7 contain a server-side open redirect vulnerability in navigateTo that fails to properly validate path-normalized payloads like /..//evil.com and /.//evil.com. Attackers can bypass external-host checks using path-normalization techniques to redirect users to attacker-controlled sites via the Location header or meta-refresh, enabling phishing and OAuth authorization-code theft.
CVSS Score
5.3
EPSS Score
0.002
Published
2026-06-22
n8n before 2.20.0 contains a credential exfiltration vulnerability in the POST /rest/dynamic-node-parameters/options endpoint that allows authenticated users to bypass Allowed HTTP Request Domains restrictions. Attackers with credential access can cause the n8n server to issue HTTP requests with credentials to unauthorized hosts, exfiltrating sensitive authentication data.
CVSS Score
5.3
EPSS Score
0.003
Published
2026-06-22
n8n before 1.123.15 and 2.5.0 contains a webhook forgery vulnerability in the GitHub Webhook Trigger node that fails to implement HMAC-SHA256 signature verification. Attackers who know the webhook URL can send unsigned POST requests to trigger workflows with arbitrary data, spoofing GitHub webhook events.
CVSS Score
6.3
EPSS Score
0.002
Published
2026-06-22
Nuxt versions 4.0.0 before 4.4.7 and 3.x before 3.21.7 accept protocol-relative paths such as //evil.com in the reloadNuxtApp function; these pass the script-protocol check but resolve to a cross-origin URL against the current page protocol. Attackers can inject paths like //evil.com to redirect users to attacker-controlled hosts, enabling phishing and OAuth authorization-code theft.
CVSS Score
5.3
EPSS Score
0.002
Published
2026-06-22
Nuxt versions 4.0.0 before 4.4.7 and 3.x before 3.21.7 fail to validate script-capable URLs in the navigateTo open option, allowing client-side script execution. Attackers can supply javascript: URLs through the open parameter to execute arbitrary scripts in the application's origin when user-controlled input is passed to navigateTo.
CVSS Score
5.3
EPSS Score
0.002
Published
2026-06-22