LiteLLM Vulnerabilities

pipLLM Inference

AI Threat Alert tracks 51 known vulnerabilities in LiteLLM, 10 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.

79
Risk Score
51
Total CVEs
10
Critical
pip
Ecosystem
Oct 27, 2026
Last CVE
51%
Patch Rate
49d
Avg Time to Patch
63,267 stars13,284 forks5,198 issues6 dependentsLast push Nov 15, 2026
View on GitHub
OpenSSF Scorecard5.8/10

Known Vulnerabilities(51 total, page 1 of 3)

SeverityCVE IDSummaryCVSSPublished
MEDIUMGHSA-hhww-mrg2-969hLiteLLM: reflected XSS in SSO debug callback6.8Oct 27, 2026HIGHGHSA-g5ff-637f-6q2mLiteLLM: file read via vertex_ai_credentials alias8.1Oct 27, 2026CRITICALCVE-2026-114612LiteLLM: forged admin token enables RCE via MCP stdio9.9Oct 22, 2026HIGHCVE-2026-59970Tandoor Recipes: SSRF via AI provider URL exposes internal network7.7Oct 16, 2026MEDIUMCVE-2026-108575LiteLLM: improper authorization in get_secret api_key6.3Oct 11, 2026MEDIUMCVE-2026-108574LiteLLM: IDOR in spend logs exposes session data4.3Oct 11, 2026HIGHCVE-2026-93355LiteLLM: JWT email fallback enables admin account takeover8.1Sep 28, 2026HIGHCVE-2026-89032LiteLLM: semantic cache tenant bypass leaks data7.7Sep 25, 2026MEDIUMCVE-2026-59823LiteLLM: SSRF via user_config api_base bypass--Sep 16, 2026MEDIUMCVE-2026-84377LiteLLM: param injection leaks provider API keys6.5Sep 2, 2026CRITICALCVE-2026-37004LiteLLM: unauth SSTI in /prompts/test enables RCE9.8Aug 27, 2026CRITICALCVE-2026-30623LiteLLM: RCE via unsanitized MCP server config9.8Jul 15, 2026HIGHCVE-2026-59822LiteLLM: MCP auth bypass via fabricated OAuth header8.2Jul 8, 2026HIGHCVE-2026-59821LiteLLM: code exec via unsandboxed Custom Guardrails7.2Jul 8, 2026MEDIUMCVE-2026-59820LiteLLM: Zip Slip in Skills upload allows file write6.5Jul 8, 2026MEDIUMCVE-2026-59819LiteLLM: admin-scope local file read via OIDC ref4.9Jul 8, 2026CRITICALGHSA-98x5-vq43-vc5psemantic-router: unpinned litellm dep pulls malware wheel--Jun 26, 2026CRITICALCVE-2026-54352Budibase: zip symlink bypass exposes all server secrets9.6Jun 22, 2026MEDIUMCVE-2026-12798litellm: SSRF in MCP OpenAPI spec loader endpoint6.3Jun 21, 2026MEDIUMCVE-2026-12796litellm: SSO session expiration allows auth persistence6.3Jun 21, 2026MEDIUMCVE-2026-12799litellm: authorization bypass exposes user list4.3Jun 21, 2026MEDIUMCVE-2026-12797litellm: auth bypass in banned keywords enterprise hook6.3Jun 21, 2026HIGHCVE-2026-12795litellm: auth bypass in SSO debug exposes LLM proxy7.3Jun 21, 2026HIGHCVE-2026-12773litellm: auth bypass in MCP proxy, no credentials required7.3Jun 21, 2026MEDIUMCVE-2026-12774litellm: SSRF in MCP server exposes cloud metadata6.3Jun 21, 2026

Showing 1–25 of 51

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 51 known CVEs, 10 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