Skip to content
CVE
by OpenHack
Browse
All CVEs
Every CVE, newest first, with filters
CVEs by company
Microsoft, Cisco, Fortinet and 840 more
CVEs by package
Open-source packages on npm, PyPI, Maven, Go…
Critical
About
Search CVEs, products, packages and vendors
/
CVEs, without the noise
One clean record per CVE, merged from the CVE List, NVD, OSV and GitHub.
Search CVEs, products, packages and vendors
Severity
Any
Published
Last 7 days
Exploited only
Search CVEs, products, packages and vendors
Severity
Any
Published
All time
Exploited only
Clear
Results for “vllm-project/vllm”
Results for “vllm-project/vllm”
136 CVEs
CVE
Record
Severity
Status
Published
CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
vllm-project vllm
High
8.8
Jun 22
CVE-2026-54233
vLLM: OOM Denial of Service via Audio Decompression Bomb
vllm-project vllm
Medium
6.5
Jun 22
CVE-2026-54236
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
vllm-project vllm
Medium
5.3
Jun 22
CVE-2026-54235
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
vllm-project vllm
Medium
6.9
Jun 22
CVE-2026-48746
vLLM: OpenAI auth bypass
vllm-project vllm
Critical
9.1
Jun 22
CVE-2026-53923
vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow
vllm-project vllm
Medium
5.3
Jun 22
CVE-2026-12491
Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
vllm-project vLLM, Red Hat AI Inference Server
Medium
4.8
Jun 17
CVE-2026-5497
Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
vllm-project/vllm
High
7.5
Jun 11
CVE-2026-4944
Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control
vllm-project/vllm
High
8.8
May 28
CVE-2026-9540
vllm-project vllm OpenAI-compatible Serving Path denial of service
vllm-project vllm
Medium
6.9
Fix available
May 26
CVE-2026-44223
vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
vllm-project vllm
Medium
6.5
May 12
CVE-2026-44222
vLLM: Remote DoS via Special-Token Placeholders
vllm-project vllm
Medium
6.5
May 12
CVE-2026-34756
vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
vllm-project vllm
Medium
6.5
Apr 6
CVE-2026-34755
vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
vllm-project vllm
Medium
6.5
Apr 6
CVE-2026-34753
vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
vllm-project vllm
Medium
5.4
Apr 6
CVE-2026-34760
vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
vllm-project vllm
Medium
5.9
Apr 2
CVE-2026-27893
vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out
vllm-project vllm
High
8.8
Mar 26
CVE-2026-25960
SSRF Protection Bypass in vLLM
vllm-project vllm
High
7.1
Mar 9
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
vllm-project vllm
Critical
9.8
Feb 2
CVE-2026-24779
vLLM vulnerable to Server-Side Request Forgery (SSRF) in `MediaConnector`
vllm-project vllm
High
7.1
Jan 27
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
vllm-project vllm
High
8.8
Jan 21
CVE-2026-22773
vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
vllm-project vllm
Medium
6.5
Jan 10
CVE-2025-66448
vLLM vulnerable to remote code execution via transformers_utils/get_config
vllm-project vllm
High
7.1
Dec 1
CVE-2025-62372
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
vllm-project vllm
High
8.3
Nov 21
CVE-2025-62426
vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
vllm-project vllm
Medium
6.5
Nov 21
CVE-2025-62164
VLLM deserialization vulnerability leading to DoS and potential RCE
vllm-project vllm
High
8.8
Nov 21
CVE-2025-6242
Vllm: server side request forgery (ssrf) in mediaconnector
Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI)
High
7.1
Oct 7
CVE-2025-59425
vLLM vulnerable to timing attack at bearer auth
vllm-project vllm
High
7.5
Oct 7
CVE-2025-48956
vLLM API endpoints vulnerable to Denial of Service Attacks
vllm-project vllm
High
7.5
Aug 21
CVE-2025-48944
vLLM Tool Schema allows DoS via Malformed pattern and type Fields
vllm-project vllm
Medium
6.5
May 30
Showing
91–120
of 136
Previous
1
2
3
4
5
Next