{"id":"CVE-2026-59822","state":"PUBLISHED","title":"LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback","description":"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.","publishedAt":"2026-07-08T19:32:18.611Z","updatedAt":"2026-09-03T03:56:05.174Z","severity":{"score":8.8,"label":"High","version":"4.0","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N","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-7488-6r32-c95q","https://github.com/BerriAI/litellm/pull/26463","https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c","https://github.com/BerriAI/litellm/releases/tag/v1.84.0","https://www.wiz.io/blog/ai-infrastructure-honeypot","https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822"],"weaknesses":["CWE-287","CWE-306"],"ingestedAt":"2026-10-29T20:12:32.778Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/59xxx/CVE-2026-59822.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-59822","state":"PUBLISHED","datePublished":"2026-07-08T19:32:18.611Z","dateUpdated":"2026-09-03T03:56:05.174Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-07-07T15:00:50.978Z"},"containers":{"cna":{"title":"LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback","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, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 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-7488-6r32-c95q","name":"https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/BerriAI/litellm/pull/26463","name":"https://github.com/BerriAI/litellm/pull/26463","tags":["x_refsource_MISC"]},{"url":"https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c","name":"https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c","tags":["x_refsource_MISC"]},{"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":"NONE","privilegesRequired":"NONE","userInteraction":"NONE","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"LOW","vulnAvailabilityImpact":"NONE","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","baseScore":8.8,"baseSeverity":"HIGH","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N","version":"4.0"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-287","lang":"en","description":"CWE-287: Improper Authentication","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-306","lang":"en","description":"CWE-306: Missing Authentication for Critical Function","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-07-08T19:32:18.611Z"},"source":{"advisory":"GHSA-7488-6r32-c95q","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","references":[{"url":"https://www.wiz.io/blog/ai-infrastructure-honeypot","tags":["third-party-advisory"]},{"url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822","tags":["government-resource"]}],"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-09-02T00:00:00+00:00","options":[{"Exploitation":"active"},{"Automatable":"yes"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3","id":"CVE-2026-59822"}}},{"other":{"type":"kev","content":{"dateAdded":"2026-09-02","reference":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-09-03T03:56:05.174Z"},"timeline":[{"time":"2026-09-02T00:00:00.000Z","lang":"en","value":"CVE-2026-59822 added to CISA KEV"}]}]}}}