litellm has 41 CVEs on record between 2024 and 2026. Disclosures have slowed: 4 in the last 90 days after 18 in the 90 before. The busiest recent month was June 2026 with 9. The median CVSS is 7.5 (high), with 8 rated critical. 10% have been exploited in the wild, in line with the corpus average. The median gap from publication to a KEV listing is 31 days (3 cases). The dominant weakness classes are CWE-266 (3) and CWE-287 (3).
CVEs per month
Last 12 months, by publish date
- Exploited share
- 10% vs 1% corpus
- Median CVSS
- 7.5
- Publish → KEV
- 31 d median(3)
- Last 90 days
- 4 prev 18
Worst active — by depth score
CVE-2026-42208Critical· 9.8LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format97CVE-2026-42271High· 8.8LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format92CVE-2026-59822High· 8.2LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format70MAL-2026-2144CriticalMalicious code in litellm (PyPI)70CVE-2026-114612Critical· 9.9LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key67
litellm vulnerabilities
CVEs affecting litellm, newest first. Open any entry for full detail, references, and exploit status.
41 CVEsRSS
GHSA-hhww-mrg2-969hMedium· 6.8LiteLLM vulnerable to reflected XSS in /sso/debug/callback
LiteLLM vulnerable to reflected XSS in /sso/debug/callback
GHSA-g5ff-637f-6q2mHigh· 8.1LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
CVE-2026-114612Critical· 9.9PoCLiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key
LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key
CVE-2026-37004Critical· 9.8LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint
LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint
CVE-2026-59822High· 8.2CISA KEVPoCLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
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 OAut…
CVE-2026-59821High· 7.2LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by th…
CVE-2026-59820Medium· 6.5LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.7-stable, LiteLLM Skills archive extraction did not sufficiently validate file paths from uploaded skill ZIP archives, allowing an authen…
CVE-2026-59819Medium· 4.9LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.10-stable, LiteLLM's /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params, a…
CVE-2026-12799Medium· 4.3BerriAI litellm: UI User Enumeration leads to System-Wide Information Disclosure
BerriAI litellm: UI User Enumeration leads to System-Wide Information Disclosure
CVE-2026-12796Medium· 6.3BerriAI litellm: SSO Login Does Not Invalidate Previous UI Session Tokens
BerriAI litellm: SSO Login Does Not Invalidate Previous UI Session Tokens
CVE-2026-12798Medium· 6.3BerriAI litellm has SSRF via Unvalidated spec_path URL in MCP OpenAPI Spec Loader
BerriAI litellm has SSRF via Unvalidated spec_path URL in MCP OpenAPI Spec Loader
CVE-2026-12797Medium· 6.3BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints
BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints
CVE-2026-12773High· 7.3LiteLLM: MCP Proxy Has Improper Authentication
LiteLLM: MCP Proxy Has Improper Authentication
CVE-2026-12770Medium· 5.4LiteLLM: Admin Key Handler Has Improper Authorization
LiteLLM: Admin Key Handler Has Improper Authorization
CVE-2026-12772Medium· 6.3LiteLLM: PROXY_ADMIN database API Key Generator Has Insufficient Session Expiration
LiteLLM: PROXY_ADMIN database API Key Generator Has Insufficient Session Expiration
CVE-2026-12771Medium· 5.0LiteLLM: M2M JWT Handler Has Improper Authorization
LiteLLM: M2M JWT Handler Has Improper Authorization
CVE-2026-49468Critical· 9.8PoCLiteLLM: Authentication Bypass via Host Header Injection
LiteLLM: Authentication Bypass via Host Header Injection
CVE-2026-47102High· 8.8PoCLiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint
LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint. While the endpoint correctly restricts users to updating only their own account, it does not restrict which fields may be changed. A user…
CVE-2026-47101High· 8.8PoCLiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit
LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified route…
CVE-2026-40217High· 8.8PoCLiteLLM has a sandbox escape in custom-code guardrail
LiteLLM has a sandbox escape in custom-code guardrail
CVE-2026-42271High· 8.8CISA KEVPoCLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /m…
CVE-2026-42208Critical· 9.8CISA KEV0dayPoCLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
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 tex…
CVE-2026-42203HighPoCLiteLLM: Server-Side Template Injection in /prompts/test endpoint
LiteLLM: Server-Side Template Injection in /prompts/test endpoint
GHSA-69x8-hrgq-fjj8HighLiteLLM: Password hash exposure and pass-the-hash authentication bypass
LiteLLM: Password hash exposure and pass-the-hash authentication bypass
CVE-2026-35030Critical· 9.1PoCLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, when JWT authentication is enabled (enable_jwt_auth: true), the OIDC userinfo cache uses token[:20] as the cache key. JWT headers prod…
CVE-2026-35029HighPoCLiteLLM: Privilege escalation via unrestricted proxy configuration endpoint
LiteLLM: Privilege escalation via unrestricted proxy configuration endpoint
MAL-2026-2144Critical⚠ ExploitedMalicious code in litellm (PyPI)
Malicious code in litellm (PyPI)
CVE-2024-10188High· 7.5LiteLLM Vulnerable to Denial of Service (DoS)
LiteLLM Vulnerable to Denial of Service (DoS)
CVE-2024-9606High· 7.5LiteLLM Reveals Portion of API Key via a Logging File
LiteLLM Reveals Portion of API Key via a Logging File
CVE-2025-0628High· 8.1LiteLLM Has an Improper Authorization Vulnerability
LiteLLM Has an Improper Authorization Vulnerability