UTC

LiteLLM

By BerriAI. 49 published vulnerabilities, 5 of them exploited in the wild.

Advisories
49
Critical
9
Exploited in the wild
5
Latest
2026-10-27
Packages it ships
Vulnerabilities
SeverityVulnerabilityPublishedFixed in
HighLiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt KeyCVE-2026-114612 · GHSA-7hp6-4w63-5g452026-10-271.101.3
HighLiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`GHSA-g5ff-637f-6q2m2026-10-271.95.0
MediumLiteLLM vulnerable to reflected XSS in /sso/debug/callbackGHSA-hhww-mrg2-969h2026-10-271.85.0
MediumLiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parametersCVE-2026-84377 · GHSA-3cv6-jpf6-82222026-09-301.88.6
MediumLiteLLM Proxy has server-side request forgery via the `user_config` request parameterCVE-2026-59823 · GHSA-hx8v-g79f-8w5f2026-09-171.83.9
CriticalLiteLLM vulnerable to server-side template injection in the /prompts/test endpointCVE-2026-37004 · GHSA-6wvf-77m9-58rm2026-08-271.83.7
LowLiteLLM: Local file read via request-supplied OIDC file referencesCVE-2026-59819 · GHSA-4g5m-c9r5-49xf2026-07-221.83.10
MediumLiteLLM: Arbitrary file write via path traversal in Skills archive extractionCVE-2026-59820 · GHSA-5jmr-gcrj-2c9q2026-07-221.83.7
LowLiteLLM: Custom Code Guardrails production endpoints bypass code safety checksCVE-2026-59821 · GHSA-72m8-9m7m-h2782026-07-221.82.0
HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbackCVE-2026-59822 · GHSA-7488-6r32-c95qExploited2026-07-221.84.0
CriticalMalicious code in litellm (PyPI)GHSA-92x9-889m-jgmw2026-07-21See advisory
LowA security vulnerability has been detected in BerriAI litellm up to 1.82.2.CVE-2026-127742026-06-21See advisory
MediumLiteLLM: MCP Proxy Has Improper AuthenticationCVE-2026-12773 · GHSA-4jcj-7x88-m9792026-06-211.84.0
LowLiteLLM: Admin Key Handler Has Improper AuthorizationCVE-2026-12770 · GHSA-6qr3-3g89-m4jj2026-06-21See advisory
LowBerriAI litellm has SSRF via Unvalidated spec_path URL in MCP OpenAPI Spec LoaderCVE-2026-12798 · GHSA-c693-x898-5g4h2026-06-21See advisory
MediumLiteLLM: SSO Debug Flow Has Improper AuthenticationCVE-2026-12795 · GHSA-j37q-q7p9-vpwm2026-06-21See advisory
LowBerriAI litellm: UI User Enumeration leads to System-Wide Information DisclosureCVE-2026-12799 · GHSA-m2v5-74w2-qhcj2026-06-21See advisory
LowLiteLLM: PROXY_ADMIN database API Key Generator Has Insufficient Session ExpirationCVE-2026-12772 · GHSA-mf52-j94g-746m2026-06-21See advisory
LowBerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async EndpointsCVE-2026-12797 · GHSA-p897-vf7j-f5h82026-06-21See advisory
LowLiteLLM: M2M JWT Handler Has Improper AuthorizationCVE-2026-12771 · GHSA-qmf3-4767-5fg32026-06-21See advisory
LowBerriAI litellm: SSO Login Does Not Invalidate Previous UI Session TokensCVE-2026-12796 · GHSA-w2mh-qq9q-453x2026-06-21See advisory
CriticalLiteLLM: Authentication Bypass via Host Header InjectionCVE-2026-49468 · GHSA-4xpc-pv4p-pm3w2026-06-161.84.0
HighLiteLLM allows an authenticated internal_user to create API keys with access to routes that their role does not permitCVE-2026-47101 · GHSA-qrc4-49gv-mv9m2026-05-211.83.14
HighLiteLLM allows a user to modify their own user_role via the /user/update endpointCVE-2026-47102 · GHSA-wpfp-gwwc-vwq62026-05-211.83.10
HighLiteLLM has a sandbox escape in custom-code guardrailCVE-2026-40217 · GHSA-wxxx-gvqv-xp7pExploited2026-05-111.83.10
HighLiteLLM: Authenticated command execution via MCP stdio test endpointsCVE-2026-42271 · GHSA-v4p8-mg3p-g94gExploited2026-04-251.83.7
CriticalLiteLLM has SQL Injection in Proxy API key verificationCVE-2026-42208 · GHSA-r75f-5x8p-qvmcExploited2026-04-241.83.7
HighLiteLLM: Server-Side Template Injection in /prompts/test endpointCVE-2026-42203 · GHSA-xqmj-j6mv-48622026-04-241.83.7
HighLiteLLM: Password hash exposure and pass-the-hash authentication bypassGHSA-69x8-hrgq-fjj82026-04-081.83.0
HighLiteLLM: Privilege escalation via unrestricted proxy configuration endpointCVE-2026-35029 · GHSA-53mr-6c8q-97892026-04-031.83.0
CriticalLiteLLM: Authentication bypass via OIDC userinfo cache key collisionCVE-2026-35030 · GHSA-jjhc-v7c2-5hh62026-04-031.83.0
CriticalTwo LiteLLM versions published containing credential harvesting malwareGHSA-5mg7-485q-xm762026-03-25See advisory
CriticalTrivy is a security scanner.CVE-2026-33634Exploited2026-03-23See advisory
MediumSQL Injection vulnerability in BerriAI LiteLLM before 1.81.0 allows attackers to execute arbitrary commands via the key parameter to the "/key/block" and "/key/unblock" API endpoints.CVE-2025-458092025-07-03See advisory
HighLiteLLM Vulnerable to Remote Code Execution (RCE)CVE-2024-6825 · GHSA-53gh-p8jc-7rg82025-03-20See advisory
HighLiteLLM Has a Leakage of Langfuse API KeysCVE-2025-0330 · GHSA-879v-fggm-vxw22025-03-20See advisory
HighLiteLLM Vulnerable to Denial of Service (DoS) via Crafted HTTP RequestCVE-2024-8984 · GHSA-fh2c-86xm-pm2x2025-03-201.56.2
HighLiteLLM Has an Improper Authorization VulnerabilityCVE-2025-0628 · GHSA-fjcf-3j3r-78rp2025-03-201.61.15
HighLiteLLM Reveals Portion of API Key via a Logging FileCVE-2024-9606 · GHSA-g5pg-73fc-hjwq2025-03-201.44.12
HighLiteLLM Vulnerable to Denial of Service (DoS)CVE-2024-10188 · GHSA-gw2q-qw9j-rgv72025-03-201.53.1.dev1
HighLiteLLM Server-Side Request Forgery (SSRF) vulnerabilityCVE-2024-6587 · GHSA-g26j-5385-hhw32024-09-131.44.8
Criticallitellm vulnerable to remote code execution based on using eval unsafelyCVE-2024-5751 · GHSA-gppg-gqw8-wh9g2024-06-271.40.16
Mediumlitellm vulnerable to improper access control in team managementCVE-2024-5710 · GHSA-qqcv-vg9f-5rr32024-06-271.40.15
HighA code injection vulnerability exists in the berriai/litellm application, version 1.34.6, due to the use of unvalidated input in the eval function within the secret management system.CVE-2024-48892024-06-061.44.16
HighArbitrary file deletion in litellmCVE-2024-4888 · GHSA-3xr8-qfvj-9p9j2024-06-061.35.36
MediumSQL injection in litellmCVE-2024-4890 · GHSA-8j42-pcfm-34672024-06-06See advisory
MediumSQL injection in litellmCVE-2024-5225 · GHSA-h6m6-jj8v-94jj2024-06-061.40.0
Highlitellm passes untrusted data to `eval` function without sanitizationCVE-2024-4264 · GHSA-7ggm-4rjg-594w2024-05-18See advisory
CriticalLiteLLM has Server-Side Template Injection vulnerability in /completions endpointCVE-2024-2952 · GHSA-46cm-pfwv-cgf82024-04-101.34.42

CVEs matched by the NVD's product names, checked 2026-11-18. Where the vendor runs the service, its fix reaches you without an update.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].

This product uses the NVD API but is not endorsed or certified by the NVD. Product facts from github.com, checked 2026-11-18. Logos are their owners' marks, shown only to identify the products.