CVE-2026-47155 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

CVE-2026-54234 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

GHSA-33CG-GXV8-3P8G vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

GHSA-3WW4-5JV9-J5GM vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

GHSA-RWXX-MRJM-WC2M vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

CVE-2026-41523 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

CVE-2026-55514 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

CVE-2026-55574 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

CVE-2026-73560

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformersutils/processors/mimov2omni.py passes attacker-controlled image and audio strings through fetchimage, requests.get, and Image.open instead of MediaConnector,...

CVE-2026-73560

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformersutils/processors/mimov2omni.py passes attacker-controlled image and audio strings through fetchimage, requests.get, and Image.open instead of MediaConnector,...

CVE-2026-73560

vLLM (an LLM inference and serving engine) prior to 0.26.0 is vulnerable to SSRF and arbitrary local file read via the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py. The _fetch_image function and audio loader pass attacker-controlled image/audio strings direc...

CVE-2026-73560 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformersutils/processors/mimov2omni.py passes attacker-controlled image and audio strings through fetchimage, requests.get, and Image.open instead of MediaConnector,...

CVE-2026-73560 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformersutils/processors/mimov2omni.py passes attacker-controlled image and audio strings through fetchimage, requests.get, and Image.open instead of MediaConnector,...

CVE-2026-71486

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generateresponses, choices, tokenids, promptlogprobs, logprobs.content, toplogprobs, a...

CVE-2026-71486 vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generateresponses, choices, tokenids, promptlogprobs, logprobs.content, toplogprobs, a...

CVE-2026-71486 vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generateresponses, choices, tokenids, promptlogprobs, logprobs.content, toplogprobs, a...

CVE-2026-71486

In vLLM versions prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints process caller-supplied GenerateResponse objects via OnlineDerenderer and tokenizer.decode before enforcing max_model_len, max_tokens, max_num_seqs, or response-size limits. An authenticated...

CVE-2026-71486

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generateresponses, choices, tokenids, promptlogprobs, logprobs.content, toplogprobs, a...

PT-2026-76797

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.26.0 Description The MiMoV2OmniMultiModalProcessor in vllm/transformers utils/processors/mimo v2 omni.py improperly handles image and audio strings. By passing attacker-controlled strings through fetch image,...

PT-2026-76775

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.26.0 Description The '/v1/completions/derender' and '/v1/chat/completions/derender' endpoints accept caller-supplied GenerateResponse objects. The generate responses, choices, token ids, prompt logprobs,...