{"id":"CVE-2026-49468","state":"PUBLISHED","title":"LiteLLM: Authentication Bypass via Host Header Injection","description":"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/auth_utils.py::get_request_route(), which Starlette reconstructs from the Host header. A crafted Host could therefore make the auth gate evaluate a different route from the one FastAPI dispatched. This vulnerability is fixed in 1.84.0.","publishedAt":"2026-06-22T20:37:14.494Z","updatedAt":"2026-07-15T00:47:34.603Z","severity":{"score":9.5,"label":"Critical","version":"4.0","vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","source":"GitHub_M"},"assigner":"GitHub_M","products":["BerriAI litellm"],"affected":[{"vendor":"BerriAI","product":"litellm","versions":[{"version":"< 1.84.0","status":"affected"}]}],"references":["https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w","https://github.com/BerriAI/litellm/releases/tag/v1.84.0","https://access.redhat.com/security/cve/CVE-2026-49468","https://bugzilla.redhat.com/show_bug.cgi?id=2491520","https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json"],"weaknesses":["CWE-290"],"ingestedAt":"2026-10-29T20:12:07.131Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/49xxx/CVE-2026-49468.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-49468","state":"PUBLISHED","datePublished":"2026-06-22T20:37:14.494Z","dateUpdated":"2026-07-15T00:47:34.603Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-05-30T04:17:43.094Z"},"containers":{"cna":{"title":"LiteLLM: Authentication Bypass via Host Header Injection","descriptions":[{"lang":"en","value":"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/auth_utils.py::get_request_route(), which Starlette reconstructs from the Host header. A crafted Host could therefore make the auth gate evaluate a different route from the one FastAPI dispatched. This vulnerability is fixed in 1.84.0."}],"affected":[{"vendor":"BerriAI","product":"litellm","versions":[{"version":"< 1.84.0","status":"affected"}]}],"references":[{"url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w","name":"https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/BerriAI/litellm/releases/tag/v1.84.0","name":"https://github.com/BerriAI/litellm/releases/tag/v1.84.0","tags":["x_refsource_MISC"]}],"metrics":[{"cvssV4_0":{"attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"PRESENT","privilegesRequired":"NONE","userInteraction":"NONE","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"HIGH","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"HIGH","subIntegrityImpact":"HIGH","subAvailabilityImpact":"HIGH","baseScore":9.5,"baseSeverity":"CRITICAL","vectorString":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","version":"4.0"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-290","lang":"en","description":"CWE-290: Authentication Bypass by Spoofing","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-07-08T19:32:42.245Z"},"source":{"advisory":"GHSA-4xpc-pv4p-pm3w","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-06-23T00:00:00+00:00","options":[{"Exploitation":"none"},{"Automatable":"yes"},{"Technical Impact":"total"}],"role":"CISA Coordinator","version":"2.0.3","id":"CVE-2026-49468"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-06-24T03:56:03.985Z"}},{"title":"litellm: LiteLLM: Authentication Bypass via Host Header Injection","descriptions":[{"lang":"en","value":"A flaw was found in LiteLLM, a proxy server (AI Gateway) used to call Large Language Model (LLM) APIs. A remote attacker could exploit a Host-header parsing vulnerability in the proxy authentication layer. By sending a crafted Host header, an attacker could gain unauthenticated access to protected management routes, potentially leading to full system compromise."}],"affected":[{"vendor":"Red Hat","product":"Exploit Intelligence","packageName":"exploit-intelligence-tech-preview/vulnerability-analysis-rhel9","defaultStatus":"affected","collectionURL":"https://access.redhat.com/downloads/content/package-browser/","cpes":["cpe:/a:redhat:exploit_intelligence:0"]},{"vendor":"Red Hat","product":"Red Hat Ansible Automation Platform 2","packageName":"ansible-automation-platform-26/lightspeed-chatbot-rhel9","defaultStatus":"affected","collectionURL":"https://access.redhat.com/downloads/content/package-browser/","cpes":["cpe:/a:redhat:ansible_automation_platform:2"]},{"vendor":"Red Hat","product":"Red Hat Ansible Automation Platform 2","packageName":"ansible-automation-platform-27/lightspeed-chatbot-rhel9","defaultStatus":"affected","collectionURL":"https://access.redhat.com/downloads/content/package-browser/","cpes":["cpe:/a:redhat:ansible_automation_platform:2"]},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","packageName":"rhoai/odh-llama-stack-core-rhel9","defaultStatus":"affected","collectionURL":"https://access.redhat.com/downloads/content/package-browser/","cpes":["cpe:/a:redhat:openshift_ai"]},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","packageName":"rhoai/odh-mlflow-rhel9","defaultStatus":"affected","collectionURL":"https://access.redhat.com/downloads/content/package-browser/","cpes":["cpe:/a:redhat:openshift_ai"]},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","packageName":"rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9","defaultStatus":"affected","collectionURL":"https://access.redhat.com/downloads/content/package-browser/","cpes":["cpe:/a:redhat:openshift_ai"]}],"references":[{"url":"https://access.redhat.com/security/cve/CVE-2026-49468","tags":["vdb-entry","x_refsource_REDHAT"]},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2491520","name":"RHBZ#2491520","tags":["issue-tracking","x_refsource_REDHAT"]},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json","tags":["x_sadp-csaf-vex"]}],"metrics":[{"other":{"content":{"namespace":"https://access.redhat.com/security/updates/classification/","value":"Important"},"type":"Red Hat severity rating"}},{"cvssV3_1":{"attackComplexity":"HIGH","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":8.1,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.1"},"format":"CVSS"}],"problemTypes":[{"descriptions":[{"cweId":"CWE-290","description":"Authentication Bypass by Spoofing","lang":"en","type":"CWE"}]}],"providerMetadata":{"shortName":"redhat-SADP","orgId":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c","dateUpdated":"2026-07-15T00:47:34.603Z"},"datePublic":"2026-06-22T20:37:14.494Z","timeline":[{"lang":"en","time":"2026-06-22T21:01:03.552Z","value":"Reported to Red Hat."},{"lang":"en","time":"2026-06-22T20:37:14.494Z","value":"Made public."}],"workarounds":[{"lang":"en","value":"To mitigate the risk of unauthenticated access, restrict network access to the LiteLLM proxy's management routes. Configure network firewalls or security groups to permit inbound connections only from trusted internal networks. This operational control limits the exposure of vulnerable endpoints to unauthorized external access. If the LiteLLM proxy is deployed behind a load balancer or API gateway, ensure these components are configured to strictly validate and sanitize the HTTP Host header before forwarding requests."}],"x_adpType":"supplier","x_generator":{"engine":"sadp-cli 1.0.0"}}]}}}