https://feed.craftedsignal.io/tags/vllm/Trending threats, MITRE ATT&CK coverage, and detection metadata — refreshed continuously.Hugoenhello@craftedsignal.iohello@craftedsignal.ioFri, 27 Mar 2026 00:16:22 +0000https://feed.craftedsignal.io/briefs/2026-03-vllm-rce/Fri, 27 Mar 2026 00:16:22 +0000hello@craftedsignal.iohttps://feed.craftedsignal.io/briefs/2026-03-vllm-rce/vLLM versions before 0.18.0 are vulnerable to remote code execution due to hardcoded trust of remote code, even when explicitly disabled by the user, allowing attackers to execute arbitrary code via malicious model repositories.vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.18.0, specifically from version 0.10.1, a critical vulnerability exists. Two model implementation files within vLLM hardcode the setting trust_remote_code=True when loading sub-components of models. This design flaw bypasses the user’s explicit security intention to disable remote code execution using the --trust-remote-code=False option. An attacker could craft a malicious model repository that…

]]>criticaladvisoryvLLMRCECVE-2026-27893