Recent Advisories

Severity ID Title Vendor Product Date Type
HIGH 7.8 MS:CVE-2026-12449

Chromium: CVE-2026-12449 Use after free in Chromoting_MS:CVE-2026-12449

This CVE was assigned by Chrome. Microsoft Edge (Chromium-based) ingests Chromium, which addresses this vulnerability. Please see Google Chrome Rel...

N/A N/A MSCVE
HIGH 8.3 MS:CVE-2026-12465

Chromium: CVE-2026-12465 Insufficient validation of untrusted input in Metrics_MS:CVE-2026-12465

This CVE was assigned by Chrome. Microsoft Edge (Chromium-based) ingests Chromium, which addresses this vulnerability. Please see Google Chrome Rel...

N/A N/A MSCVE
MEDIUM 5.3 CVE-2026-54236

vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router_CVE-2026-54236

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a saniti...

vllm-project vllm < 0.23.1rc0 CVE
MEDIUM 6.9 CVE-2026-54235

vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels_CVE-2026-54235

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operat...

vllm-project vllm < 0.23.1rc0 CVE
MEDIUM 6.5 CVE-2026-54233

vLLM: OOM Denial of Service via Audio Decompression Bomb_CVE-2026-54233

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compr...

vllm-project vllm < 0.23.1rc0 CVE
HIGH 8.8 CVE-2026-54232

vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile_CVE-2026-54232

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 confus...

vllm-project vllm < 0.22.1 CVE
MEDIUM 5.3 CVE-2026-53923

vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow_CVE-2026-53923

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 vL...

vllm-project vllm >= 0.5.5, < 0.23.1rc0 CVE
CRITICAL 9.1 CVE-2026-48746

vLLM: OpenAI auth bypass_CVE-2026-48746

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 starlett...

vllm-project vllm >= 0.3.0, < 0.22.0 CVE
MEDIUM 6.5 CVE-2026-47155

vLLM: Artifact Pin Decay in vLLM allows pinned deployments to load unpinned code, weights, and processors_CVE-2026-47155

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 app...

vllm-project vllm < 0.22.0 CVE
HIGH 7.5 CVE-2026-41523

vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution_CVE-2026-41523

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 func...

vllm-project vllm < 0.22.0 CVE