Multiple critical security vulnerabilities have been disclosed for the LITELLM library, a popular open-source tool for...
Multiple critical security vulnerabilities have been disclosed for the LITELLM library, a popular open-source tool for interfacing with LLM API providers.
confidence score
Strong evidence: 2 independent source classes support this read.
signal brief
Multiple critical security vulnerabilities have been disclosed for the LITELLM library, a popular open-source tool for interfacing with LLM API providers. The vulnerabilities, published on July 7, 2026, include authentication bypass (CVE-2026-49468), remote code execution (CVE-2024-6825), SQL injection (CVE-2024-4890), arbitrary file deletion (CVE-2024-4888), and denial of service (CVE-2024-8984). These issues allow attackers to bypass authentication, execute arbitrary code, delete files, inject SQL, or cause service disruption. The vulnerabilities affect versions prior to the latest release (1.92.0, July 12, 2026), which may contain fixes. Users are urged to patch immediately. The cumulative security risk could erode trust in LITELLM and prompt migration to alternative LLM gateway solutions, representing a negative signal for the developer ecosystem around AI infrastructure.
What the sources said
- OSV advisory GHSA-4xpc-pv4p-pm3w: "LiteLLM: Authentication Bypass via Host Header Injection" (source)
- OSV advisory PYSEC-2026-1541: "LiteLLM Vulnerable to Remote Code Execution (RCE)" (source)
- OSV advisory PYSEC-2026-1544: "SQL injection in litellm" (source)
- PyPI release 1.92.0: new version on July 12, likely addressing these issues (source)
source data used
“Library to easily interface with LLM API providers”
“Aliases: CVE-2026-49468, PYSEC-2026-388 LiteLLM: Authentication Bypass via Host Header Injection”
“Aliases: CVE-2024-4888, GHSA-3xr8-qfvj-9p9j Arbitrary file deletion in litellm”
“Aliases: CVE-2024-6825, GHSA-53gh-p8jc-7rg8 LiteLLM Vulnerable to Remote Code Execution (RCE)”
“Aliases: CVE-2024-4264, GHSA-7ggm-4rjg-594w litellm passes untrusted data to `eval` function without sanitization”
“Aliases: CVE-2025-0330, GHSA-879v-fggm-vxw2 LiteLLM Has a Leakage of Langfuse API Keys”
“Aliases: CVE-2024-4890, GHSA-8j42-pcfm-3467 SQL injection in litellm”
“Aliases: CVE-2024-8984, GHSA-fh2c-86xm-pm2x LiteLLM Vulnerable to Denial of Service (DoS) via Crafted HTTP Request”
“Aliases: CVE-2025-0628, GHSA-fjcf-3j3r-78rp LiteLLM Has an Improper Authorization Vulnerability”
“Aliases: CVE-2024-6587, GHSA-g26j-5385-hhw3 LiteLLM Server-Side Request Forgery (SSRF) vulnerability”
“Aliases: CVE-2024-9606, GHSA-g5pg-73fc-hjwq LiteLLM Reveals Portion of API Key via a Logging File”
“Aliases: CVE-2024-10188, GHSA-gw2q-qw9j-rgv7 LiteLLM Vulnerable to Denial of Service (DoS)”
“Aliases: CVE-2024-5225, GHSA-h6m6-jj8v-94jj SQL injection in litellm”
“Aliases: CVE-2024-5710, GHSA-qqcv-vg9f-5rr3 litellm vulnerable to improper access control in team management”
“Aliases: CVE-2024-2952, GHSA-46cm-pfwv-cgf8 LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint”
“Aliases: CVE-2026-49468, GHSA-4xpc-pv4p-pm3w LiteLLM: Authentication Bypass via Host Header Injection”
“Aliases: CVE-2024-5751, GHSA-gppg-gqw8-wh9g litellm vulnerable to remote code execution based on using eval unsafely”
“Aliases: CVE-2026-35030, GHSA-jjhc-v7c2-5hh6 LiteLLM: Authentication bypass via OIDC userinfo cache key collision”
“Aliases: CVE-2026-42208, GHSA-r75f-5x8p-qvmc LiteLLM has SQL Injection in Proxy API key verification”
Decision support, not stock advice. This signal is research with cited evidence — not a recommendation to buy, sell, or hold any security.