LiteLLM Vulnerabilities

pip LLM Inference

AI Threat Alert tracks 35 known vulnerabilities in LiteLLM, 7 rated critical — an AI/ML llm inference in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

Data sources
79
Risk Score
35
Total CVEs
7
Critical
pip
Ecosystem
Jun 26, 2026
Last CVE
46%
Patch Rate
48d
Avg Time to Patch
51,793 stars 9,245 forks 3,471 issues 6 dependents Last push Jun 28, 2026
View on GitHub
OpenSSF Scorecard 6.0/10

Known Vulnerabilities (35 total, page 1 of 2)

Severity CVE ID Summary CVSS Published
CRITICAL GHSA-98x5-vq43-vc5p semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin -- Jun 26, 2026 CRITICAL CVE-2026-54352 Budibase: zip symlink bypass exposes all server secrets 9.6 Jun 22, 2026 MEDIUM CVE-2026-12798 litellm: SSRF in MCP OpenAPI spec loader endpoint 6.3 Jun 21, 2026 MEDIUM CVE-2026-12796 litellm: SSO session expiration allows auth persistence 6.3 Jun 21, 2026 MEDIUM CVE-2026-12799 litellm: authorization bypass exposes user list 4.3 Jun 21, 2026 MEDIUM CVE-2026-12797 litellm: auth bypass in banned keywords enterprise hook 6.3 Jun 21, 2026 HIGH CVE-2026-12795 litellm: auth bypass in SSO debug exposes LLM proxy 7.3 Jun 21, 2026 HIGH CVE-2026-12773 litellm: auth bypass in MCP proxy, no credentials required 7.3 Jun 21, 2026 MEDIUM CVE-2026-12774 litellm: SSRF in MCP server exposes cloud metadata 6.3 Jun 21, 2026 MEDIUM CVE-2026-12772 litellm: session expiration bypass in proxy auth 6.3 Jun 21, 2026 HIGH CVE-2026-12771 litellm: JWT auth bypass in M2M proxy handler 7.5 Jun 21, 2026 HIGH CVE-2026-12770 litellm: auth bypass in Admin Key Handler endpoint 8.8 Jun 21, 2026 CRITICAL CVE-2026-49468 LiteLLM: auth bypass via Host header spoofing 8.1 Jun 16, 2026 HIGH CVE-2026-47102 LiteLLM: privilege escalation to proxy_admin via /user/update 8.8 May 21, 2026 HIGH CVE-2026-47101 LiteLLM: RBAC bypass enables proxy admin escalation 8.8 May 21, 2026 HIGH CVE-2026-42271 LiteLLM: RCE via MCP test endpoint command injection 8.8 May 8, 2026 CRITICAL CVE-2026-42208 LiteLLM: SQL injection exposes LLM API credentials 9.8 May 8, 2026 HIGH CVE-2026-42203 LiteLLM: SSTI in prompt template endpoint enables RCE 8.8 May 8, 2026 HIGH GHSA-v4p8-mg3p-g94g litellm: RCE via MCP test endpoints privilege bypass -- Apr 25, 2026 HIGH GHSA-xqmj-j6mv-4862 LiteLLM: RCE via unsandboxed prompt template rendering -- Apr 24, 2026 CRITICAL GHSA-r75f-5x8p-qvmc litellm: SQLi exposes all managed LLM API credentials -- Apr 24, 2026 HIGH CVE-2026-40217 LiteLLM: RCE via bytecode rewriting in guardrails API 8.8 Apr 10, 2026 HIGH GHSA-69x8-hrgq-fjj8 LiteLLM: auth bypass chain enables full privilege escalation -- Apr 8, 2026 HIGH CVE-2026-35029 LiteLLM: auth bypass allows RCE and full takeover 8.8 Apr 3, 2026 CRITICAL CVE-2026-35030 LiteLLM: auth bypass via JWT cache key collision 9.1 Apr 3, 2026

Showing 1–25 of 35

Frequently asked questions

What is LiteLLM?

LiteLLM is an AI/ML llm inference tracked by AI Threat Alert for security vulnerabilities in the pip ecosystem.

How many known vulnerabilities does LiteLLM have?

LiteLLM has 35 known CVEs, 7 of them critical, tracked from NVD and GitHub Advisory.

Which ecosystem is LiteLLM distributed in?

LiteLLM is distributed via the pip ecosystem and categorized as llm inference.

Where does the LiteLLM vulnerability data come from?

Vulnerability data is sourced from NVD and GitHub Advisory, enriched with CVSS, EPSS, exploit signals, and patch status for each CVE.

How do I assess the risk of LiteLLM?

Review each CVE below — every entry shows CVSS severity, EPSS exploit probability, exploitation signals, and whether a patched version is available.

Monitor LiteLLM in your stack

Get instant alerts when new vulnerabilities affect LiteLLM. CISO analysis, ATLAS technique mappings, and compliance reports included.

Start Monitoring