{"id":"CVE-2026-42208","aliases":["GHSA-r75f-5x8p-qvmc","PYSEC-2026-391"],"summary":"LiteLLM: SQL injection in Proxy API key verification","published_at":"2026-04-24T16:17:07Z","modified_at":"2026-10-05T18:45:06.017895Z","products":[],"rating":{"severity":"critical","score":9.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","attack_path":"internet_unauthenticated","user_interaction":false,"malicious":false,"red_hat":"Critical","vendor_ratings":[{"source":"Red Hat","rating":"Critical"}]},"fix_available":false,"kev":{"listed":true,"date_added":"2026-05-08T00:00:00Z","due_date":"2026-05-11T00:00:00Z","ransomware":false,"required_action":"Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable."},"public_exploit":false,"exploits":[{"source":"nuclei-templates","id":"http/cves/2026/CVE-2026-42208","name":"LiteLLM - SQL Injection","url":"https://github.com/projectdiscovery/nuclei-templates/blob/main/http/cves/2026/CVE-2026-42208.yaml","verified":false}],"epss":{"score":0.8942000269889832,"percentile":0.9979000091552734,"date":"2026-11-19T00:00:00Z"},"priority":33.8,"details":"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.","affected_stack":[],"affected_other":[{"ecosystem":"CVE","package":"BerriAI/litellm","versions":[">= 1.81.16, < 1.83.7"],"provider":"cvelistv5","source":"CVE-2026-42208","relation":"self"},{"ecosystem":"NVD","package":"litellm:litellm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.81.16"},{"fixed":"1.83.7"}]}],"fixed":["1.83.7"],"provider":"nvd","source":"CVE-2026-42208","relation":"self"},{"ecosystem":"PyPI","package":"litellm","purl":"pkg:pypi/litellm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.81.16"},{"fixed":"1.83.7"}]}],"versions":["1.81.16","1.82.0","1.82.1","1.82.2","1.82.3","1.82.4","1.82.5","1.82.6","1.83.0","1.83.1","1.83.2","1.83.3","1.83.4","1.83.5","1.83.6"],"fixed":["1.83.7"],"provider":"osv","source":"GHSA-r75f-5x8p-qvmc","relation":"self"},{"ecosystem":"PyPI","package":"litellm","purl":"pkg:pypi/litellm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.81.16"},{"fixed":"1.83.7"}]}],"versions":["1.81.16","1.82.0","1.82.1","1.82.2","1.82.3","1.82.4","1.82.5","1.82.6","1.83.0","1.83.1","1.83.2","1.83.3","1.83.4","1.83.5","1.83.6"],"fixed":["1.83.7"],"provider":"osv","source":"PYSEC-2026-391","relation":"self"}],"product_status":[{"vendor":"Red Hat","product":"Lightspeed Core","cpe":"cpe:/a:redhat:lightspeed_core","status":"not_affected","packages":["lightspeed-core/lightspeed-stack-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-42208"},{"vendor":"Red Hat","product":"Red Hat Ansible Automation Platform 2","cpe":"cpe:/a:redhat:ansible_automation_platform:2","status":"not_affected","packages":["ansible-automation-platform-26/lightspeed-chatbot-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-42208"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"not_affected","packages":["rhoai/odh-llama-stack-core-rhel9","rhoai/odh-mlflow-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-42208"}],"records":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-1288","relation":"upstream","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-1288","license":"TLP:CLEAR, mirroring permitted","published_at":"2026-04-27T22:00:00Z","modified_at":"2026-06-25T22:00:00Z","summary":"LiteLLM: Mehrere Schwachstellen","details":"Ein Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um einen SQL-Injection-Angriff durchzuführen und sich unbefugten Zugriff zu verschaffen oder um beliebigen Programmcode mit den Rechten des Dienstes auszuführen\n\nLiteLLM ist ein Gateway, das eine einheitliche Schnittstelle für verschiedene Large Language Models (LLMs) bietet.","severity":[{"type":"BSI","score":"kritisch","source":"WID-SEC-W-2026-1288"}],"affected":[],"product_status":[],"references":[{"type":"WEB","url":"https://wid.cert-bund.de/.well-known/csaf/white/2026/wid-sec-w-2026-1288.json"},{"type":"WEB","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-1288"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"WEB","url":"https://webflow.sysdig.com/blog/cve-2026-42208-targeted-sql-injection-against-litellms-authentication-path-discovered-36-hours-following-vulnerability-disclosure"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-v4p8-mg3p-g94g"},{"type":"WEB","url":"https://www.cisa.gov/news-events/alerts/2026/06/08/cisa-adds-two-known-exploited-vulnerabilities-catalog"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:27784"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:30056"}]},{"provider":"cvelistv5","source_id":"CVE-2026-42208","relation":"self","url":"https://www.cve.org/CVERecord?id=CVE-2026-42208","license":"CC-BY-4.0","published_at":"2026-05-08T03:38:14.124Z","modified_at":"2026-07-15T00:58:03.861Z","summary":"LiteLLM: SQL injection in Proxy API key verification","details":"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.","severity":[{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","source":"CVE-2026-42208"},{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","source":"redhat-SADP:CVE-2026-42208"}],"affected":[{"ecosystem":"CVE","package":"BerriAI/litellm","versions":[">= 1.81.16, < 1.83.7"],"provider":"cvelistv5","source":"CVE-2026-42208","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable"}]},{"provider":"nvd","source_id":"CVE-2026-42208","relation":"self","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-42208","severity":[],"affected":[{"ecosystem":"NVD","package":"litellm:litellm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.81.16"},{"fixed":"1.83.7"}]}],"fixed":["1.83.7"],"provider":"nvd","source":"CVE-2026-42208","relation":"self"}],"product_status":[],"references":[]},{"provider":"osv","source_id":"GHSA-r75f-5x8p-qvmc","relation":"self","url":"https://osv.dev/vulnerability/GHSA-r75f-5x8p-qvmc","license":"CC-BY-4.0","published_at":"2026-04-24T16:17:07Z","modified_at":"2026-10-05T18:45:06.017895Z","summary":"LiteLLM has SQL Injection in Proxy API key verification","details":"### Impact\n\nA database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted `Authorization` header to any LLM API route (for example `POST /chat/completions`) and reach this query through the proxy's error-handling path.\n\nAn attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages.\n\n### Patches\n\nFixed in **`1.83.7`**. The caller-supplied value is now always passed to the database as a separate parameter. Upgrade to `1.83.7` or later.\n\n### Workarounds\n\nIf upgrading is not immediately possible, set `disable_error_logs: true` under `general_settings`. This removes the path through which unauthenticated input reaches the vulnerable query.\n\n### References\n\n- Patched release: [`v1.83.7-stable`](https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable)\n\n**Discovery Credit**: Tencent YunDing Security Lab","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","source":"GHSA-r75f-5x8p-qvmc"},{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","source":"GHSA-r75f-5x8p-qvmc"}],"affected":[{"ecosystem":"PyPI","package":"litellm","purl":"pkg:pypi/litellm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.81.16"},{"fixed":"1.83.7"}]}],"versions":["1.81.16","1.82.0","1.82.1","1.82.2","1.82.3","1.82.4","1.82.5","1.82.6","1.83.0","1.83.1","1.83.2","1.83.3","1.83.4","1.83.5","1.83.6"],"fixed":["1.83.7"],"provider":"osv","source":"GHSA-r75f-5x8p-qvmc","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-42208"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-42208"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2463965"},{"type":"PACKAGE","url":"https://github.com/BerriAI/litellm"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-391.yaml"},{"type":"WEB","url":"https://pypi.org/project/litellm"},{"type":"WEB","url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208"}]},{"provider":"osv","source_id":"PYSEC-2026-391","relation":"self","url":"https://osv.dev/vulnerability/PYSEC-2026-391","license":"CC-BY-4.0","published_at":"2026-06-29T11:50:45.645996Z","modified_at":"2026-07-01T20:22:56.429351Z","summary":"LiteLLM has SQL Injection in Proxy API key verification","details":"### Impact\n\nA database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted `Authorization` header to any LLM API route (for example `POST /chat/completions`) and reach this query through the proxy's error-handling path.\n\nAn attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages.\n\n### Patches\n\nFixed in **`1.83.7`**. The caller-supplied value is now always passed to the database as a separate parameter. Upgrade to `1.83.7` or later.\n\n### Workarounds\n\nIf upgrading is not immediately possible, set `disable_error_logs: true` under `general_settings`. This removes the path through which unauthenticated input reaches the vulnerable query.\n\n### References\n\n- Patched release: [`v1.83.7-stable`](https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable)\n \n**Discovery Credit**: Tencent YunDing Security Lab","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","source":"PYSEC-2026-391"},{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","source":"PYSEC-2026-391"}],"affected":[{"ecosystem":"PyPI","package":"litellm","purl":"pkg:pypi/litellm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"1.81.16"},{"fixed":"1.83.7"}]}],"versions":["1.81.16","1.82.0","1.82.1","1.82.2","1.82.3","1.82.4","1.82.5","1.82.6","1.83.0","1.83.1","1.83.2","1.83.3","1.83.4","1.83.5","1.83.6"],"fixed":["1.83.7"],"provider":"osv","source":"PYSEC-2026-391","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-42208"},{"type":"PACKAGE","url":"https://github.com/BerriAI/litellm"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable"},{"type":"WEB","url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208"},{"type":"PACKAGE","url":"https://pypi.org/project/litellm"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-r75f-5x8p-qvmc"}]},{"provider":"redhat-vex","source_id":"CVE-2026-42208","relation":"self","url":"https://access.redhat.com/security/cve/CVE-2026-42208","license":"CC-BY-4.0","published_at":"2026-04-28T00:00:00Z","modified_at":"2026-05-08T19:20:12Z","summary":"LiteLLM: LiteLLM: Unauthorized data access and modification via SQL injection","details":"A flaw was found in LiteLLM. A database query used for proxy API key checks incorrectly incorporated caller-supplied key values directly into the query. This vulnerability allows an unauthenticated attacker to send a specially crafted Authorization header to any Large Language Model (LLM) API route, exploiting the proxy's error-handling path. Successful exploitation could enable the attacker to read and potentially modify data within the proxy's database, leading to unauthorized access to the proxy and its managed credentials.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","source":"CVE-2026-42208"},{"type":"Red Hat","score":"Critical","source":"CVE-2026-42208"}],"affected":[],"product_status":[{"vendor":"Red Hat","product":"Lightspeed Core","cpe":"cpe:/a:redhat:lightspeed_core","status":"not_affected","packages":["lightspeed-core/lightspeed-stack-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-42208"},{"vendor":"Red Hat","product":"Red Hat Ansible Automation Platform 2","cpe":"cpe:/a:redhat:ansible_automation_platform:2","status":"not_affected","packages":["ansible-automation-platform-26/lightspeed-chatbot-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-42208"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"not_affected","packages":["rhoai/odh-llama-stack-core-rhel9","rhoai/odh-mlflow-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-42208"}],"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42208.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-42208"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2463965"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-42208"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-42208"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"WEB","url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog"}]}],"references":[{"type":"WEB","url":"https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"WEB","url":"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-42208"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-42208"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2463965"},{"type":"PACKAGE","url":"https://github.com/BerriAI/litellm"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-r75f-5x8p-qvmc"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-391.yaml"},{"type":"WEB","url":"https://pypi.org/project/litellm"},{"type":"WEB","url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208"},{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42208.json"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-42208"},{"type":"WEB","url":"https://www.cisa.gov/known-exploited-vulnerabilities-catalog"}],"sources":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-1288","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-1288","license":"TLP:CLEAR, mirroring permitted","modified_at":"2026-06-25T22:00:00Z","relation":"upstream"},{"provider":"cvelistv5","source_id":"CVE-2026-42208","url":"https://www.cve.org/CVERecord?id=CVE-2026-42208","license":"CC-BY-4.0","modified_at":"2026-07-15T00:58:03.861Z","relation":"self"},{"provider":"nvd","source_id":"CVE-2026-42208","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-42208","relation":"self"},{"provider":"osv","source_id":"GHSA-r75f-5x8p-qvmc","url":"https://osv.dev/vulnerability/GHSA-r75f-5x8p-qvmc","license":"CC-BY-4.0","modified_at":"2026-10-05T18:45:06.017895Z","relation":"self"},{"provider":"osv","source_id":"PYSEC-2026-391","url":"https://osv.dev/vulnerability/PYSEC-2026-391","license":"CC-BY-4.0","modified_at":"2026-07-01T20:22:56.429351Z","relation":"self"},{"provider":"redhat-vex","source_id":"CVE-2026-42208","url":"https://access.redhat.com/security/cve/CVE-2026-42208","license":"CC-BY-4.0","modified_at":"2026-05-08T19:20:12Z","relation":"self"}]}
