EUVD-2026-60377

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor fetchimage and audio loader bypass MediaConnector protections...

GHSA-4HHP-H66F-J5J7 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary vllm/transformersutils/processors/mimov2omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get... directly on user-supplied image and audio URL strings and Image.open... on user-supplied local paths, without the SSRF / allowedlocalmediapath checks that...

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary vllm/transformersutils/processors/mimov2omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get... directly on user-supplied image and audio URL strings and Image.open... on user-supplied local paths, without the SSRF / allowedlocalmediapath checks that...

GHSA-7M6H-X95X-82Q5 vLLM: Cross-User Data Leak Vulnerability

Summary An integer overflow in the actandmulkernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first...

EUVD-2026-58066

vLLM: Cross-User Data Leak Vulnerability...

GHSA-PR7F-P5MW-FC87 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive Summary The follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.checksparsetensorinvariants, but PyTorch 2.11.0 implements that context...

EUVD-2026-58064

vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts...

EUVD-2026-58063

vLLM: ReDoS via structuredoutputs.regex in the lm-format-enforcer backend no compile timeout — missed sibling of GHSA-rwxx-mrjm-wc2m...

GHSA-48JH-3GJ7-FG8V vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m

Summary The fix for GHSA-rwxx-mrjm-wc2m "ReDoS via structuredoutputs.regex compiled without timeout" wrapped the regex compile in the xgrammar and outlines backends with compileregexwithtimeout and, for outlines, validateregexisbuildable. The lm-format-enforcer backend was left unguarded: it...

EUVD-2026-58053

vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages...

GHSA-HWRM-C4CX-RF4J vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages

Summary When the vLLM API receives a malformed request e.g., invalid JSON or missing required fields, FastAPI raises a Pydantic RequestValidationError. The validationexceptionhandler in vllm/entrypoints/openai/serverutils.py converts this exception to a string via strexc, which includes the...

EUVD-2026-60376

vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds...

GHSA-8737-QX52-HJFF vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

Summary The /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects and postprocess every nested choices.tokenids list directly. Unlike the normal render/generate path, derender does not enforce model context length, resolved maxtokens,...

GHSA-83VM-P52W-F9PW vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9...

CVE-2026-44223 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9...

CVE-2026-37237

A flaw was found in vLLM. Remote attackers can exploit this vulnerability by providing a URL to an excessively large media file. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions, responsible for fetching user-supplied media, do not limit the response size. This oversight allows a...

CVE-2026-37237

vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read without enforcing a maximum response...

CVE-2026-37237

vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read without enforcing a maximum response...

CVE-2026-37237

vLLM (versions up to and including 0.17.0 ) is vulnerable to a Denial of Service via memory exhaustion . The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read() without enforcing a maximum response ...

EUVD-2026-67775

vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetchaudio and AsyncMediaIO.fetchimage functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read without enforcing a maximum response...