litellm1.82.8

tar.gz

Published Mar 24, 2026 • Policy compliance

pypi Registry

Developer Trust Score

N/A

Recommended Version:

x.y.z

Recommended upgrade that meets your policy.

Compare Versions

Overview

Versions: 1,401

Vulnerabilities

16

Dependencies

0

Severity

• Critical (4)
• High (0)
• Medium (0)
• Low (0)

CVSS Score

0.0

EPSS Score

0.0

Malware

All

KEV Status

All
Known Exploited Not in KEV Catalog: No known exploits

Published

All
Last 7 days
Last 30 days
Last 60 days
Last 90 days
Last 6 months
Last year
Last 2 years

Filter

Sort: Published (Newest first)

• Published (Newest first)
• Published (Oldest first)
• CVSS Score (Critical to Low)
• CVSS Score (Low to Critical)

Vulnerability Reports

CVE-2026-30623

• LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality. The application allows users to add MCP servers via a JSON configuration specifying arbitrary command and args values. LiteLLM executes these values on the host without validation, enabling attackers to run arbitrary operating system commands. Successful exploitation may result in remote code execution with the privileges of the LiteLLM process.
• Severity: Critical
• Published: Jul 20, 2026

CVE-2026-49468

• 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.
• Severity: Critical
• Published: Jun 18, 2026

CVE-2026-42208

• litellm - SQL injection via unsanitized proxy API key check
• Severity: Critical
• Published: Apr 27, 2026

CVE-2026-35030

• 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 produced by the same signing algorithm generate identical first 20 characters. This configuration option is not enabled by default. Most instances are not affected. An unauthenticated attacker can craft a token whose first 20 characters match a legitimate user's cached token. On cache hit, the attacker inherits the legitimate user's identity and permissions. This affects deployments with JWT/OIDC authentication enabled. Fixed in v1.83.0.
• Severity: Critical
• Published: Apr 5, 2026

litellm 1.82.8 | Vulnerabilities | Sonatype Guide