Multiple security advisories have been published for LiteLLM, an open-source library for interfacing with LLM API...

Multiple security advisories have been published for LiteLLM, an open-source library for interfacing with LLM API providers. The vulnerabilities include authentication bypass via host header injection (CVE-2026-49468), server-side template injection in the /completions endpoint (CVE-2024-2952), remote code execution via unsafe eval (CVE-2024-5751), authentication bypass via OIDC userinfo cache key collision (CVE-2026-35030), and SQL injection in proxy API key verification (CVE-2026-42208). These vulnerabilities pose significant security risks to users, potentially allowing unauthorized access, privilege escalation, or data breaches. The advisories were published on OSV.dev between June 16 and June 29, 2026. A new PyPI release, litellm 1.90.3, was made on July 3, 2026, which may include fixes, but the advisories indicate that prior versions are affected.

What the sources said:

• OSV advisory GHSA-4xpc-pv4p-pm3w: "LiteLLM: Authentication Bypass via Host Header Injection"
• OSV advisory PYSEC-2026-387: "LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint"
• OSV advisory PYSEC-2026-389: "litellm vulnerable to remote code execution based on using eval unsafely"
• OSV advisory PYSEC-2026-390: "LiteLLM: Authentication bypass via OIDC userinfo cache key collision"
• OSV advisory PYSEC-2026-391: "LiteLLM has SQL Injection in Proxy API key verification"