https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Fri, 02 Oct 2026 20:31:07 +0000 https://cve.radiocsirt.org/vuln/euvd-2026-329248 EUVD-2026-329248 https://cve.radiocsirt.org/vuln/euvd-2026-329248 https://cve.radiocsirt.org/vuln/fkie_cve-2026-54232 <p>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 confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY=&#34;unsafe-best-match&#34; is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.</p> <p>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 confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY=&#34;unsafe-best-match&#34; is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-54232 https://cve.radiocsirt.org/vuln/pysec-2026-227 <p><strong>Affected:</strong> PyPI: vllm</p> <p>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 confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY=&#34;unsafe-best-match&#34; is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.</p> <p><strong>Affected:</strong> PyPI: vllm</p> <p>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 confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY=&#34;unsafe-best-match&#34; is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.</p> https://cve.radiocsirt.org/vuln/pysec-2026-227 https://cve.radiocsirt.org/vuln/wid-sec-w-2026-1860 <p>Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um beliebigen Programmcode mit Administratorrechten auszuführen.</p> <p>Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um beliebigen Programmcode mit Administratorrechten auszuführen.</p> https://cve.radiocsirt.org/vuln/wid-sec-w-2026-1860