Known Vulnerabilities for Inference by Xorbitsai
Listed below are 10 of the newest known vulnerabilities associated with "Inference" by "Xorbitsai".
These CVEs are retrieved based on exact matches on listed software, hardware, and vendor information (CPE data) as well as a keyword search to ensure the newest vulnerabilities with no officially listed software information are still displayed.
Data on known vulnerable versions is also displayed based on information from known CPEs
Known Vulnerabilities
| CVE | Shortened Description | Severity | Publish Date | Last Modified |
|---|---|---|---|---|
| CVE-2026-73560 json | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm... | Not Provided | 2026-08-17 | 2026-08-18 |
| CVE-2026-73559 json | vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRe... | Not Provided | 2026-08-13 | 2026-08-14 |
| CVE-2026-73558 json | vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d... | Not Provided | 2026-08-13 | 2026-08-13 |
| CVE-2026-73557 json | vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safe_load_prompt_embeds in vl... | Not Provided | 2026-08-13 | 2026-08-13 |
| CVE-2026-73556 json | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in... | Not Provided | 2026-08-13 | 2026-08-14 |
| CVE-2026-73555 json | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/... | Not Provided | 2026-08-13 | 2026-08-14 |
| CVE-2026-72852 json | hank-ai/darknet sizes a convolutional layer's weight and output heap buffers by multiplying configuration fields taken from a... | Not Provided | 2026-08-20 | 2026-08-20 |
| CVE-2026-72642 json | The native inference process that Elasticsearch uses to evaluate uploaded machine learning models accepts a model operation t... | Not Provided | 2026-08-13 | 2026-08-14 |
| CVE-2026-72629 json | Authorization Bypass Through User-Controlled Key (CWE-639) in Kibana can lead to unauthorized cross-space access via Accessin... | Not Provided | 2026-08-13 | 2026-08-13 |
| CVE-2026-71486 json | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat... | Not Provided | 2026-08-17 | 2026-08-18 |