Credenzo GitHub

mcp-audit is becoming Credenzo, the taste test for agent tools. The package is still mcp-audit-scanner and the command is still mcp-audit.

Is litellm safe?

31 fixed advisories Facts from the Credenzo registry about the pypi package litellm. The same data is served as JSON.

Check it from your terminal

mcp-audit vet litellm --ecosystem pypi

Offline: it uses the registry bundled with Credenzo. mcp-audit update-registry fetches the newest one.

Registry facts

MaintainerBerriAI
Verified publisherno
Entry last checked2026-10-29
Hash pinsnone recorded
Provenance expectedno
Repositoryhttps://github.com/BerriAI/litellm

Recorded advisories 31

Advisories for litellm
AdvisoryCVSSSummaryFixed in
CVE-2024-10188not recordedLiteLLM Vulnerable to Denial of Service (DoS)1.53.1.dev1
CVE-2024-2952not recordedLiteLLM has Server-Side Template Injection vulnerability in /completions endpoint1.34.42
CVE-2024-4888not recordedArbitrary file deletion in litellm1.35.36
CVE-2024-5225not recordedSQL injection in litellm1.40.0
CVE-2024-5710not recordedlitellm vulnerable to improper access control in team management1.40.15
CVE-2024-5751not recordedlitellm vulnerable to remote code execution based on using eval unsafely1.40.16
CVE-2024-6587not recordedLiteLLM Server-Side Request Forgery (SSRF) vulnerability1.44.8
CVE-2024-8984not recordedLiteLLM Vulnerable to Denial of Service (DoS) via Crafted HTTP Request1.56.2
CVE-2024-9606not recordedLiteLLM Reveals Portion of API Key via a Logging File1.44.12
CVE-2025-0628not recordedLiteLLM Has an Improper Authorization Vulnerability1.61.15
CVE-2026-114612not recordedLiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key1.104.0rc2
CVE-2026-12773not recordedLiteLLM: MCP Proxy Has Improper Authentication1.84.0
CVE-2026-35029not recordedLiteLLM: Privilege escalation via unrestricted proxy configuration endpoint1.83.0
CVE-2026-35030not recordedLiteLLM: Authentication bypass via OIDC userinfo cache key collision1.83.0
CVE-2026-37004not recordedLiteLLM vulnerable to server-side template injection in the /prompts/test endpoint1.83.7
CVE-2026-40217not recordedLiteLLM has a sandbox escape in custom-code guardrail1.83.10
CVE-2026-42203not recordedLiteLLM: Server-Side Template Injection in /prompts/test endpoint1.83.7
CVE-2026-42208not recordedLiteLLM has SQL Injection in Proxy API key verification1.83.7
CVE-2026-42271not recordedLiteLLM: Authenticated command execution via MCP stdio test endpoints1.83.7
CVE-2026-47101not recordedLiteLLM allows an authenticated internal_user to create API keys with access to routes that their role does not permit1.83.14
CVE-2026-47102not recordedLiteLLM allows a user to modify their own user_role via the /user/update endpoint1.83.10
CVE-2026-49468not recordedLiteLLM: Authentication Bypass via Host Header Injection1.84.0
CVE-2026-59819not recordedLiteLLM: Local file read via request-supplied OIDC file references1.83.10
CVE-2026-59820not recordedLiteLLM: Arbitrary file write via path traversal in Skills archive extraction1.83.7
CVE-2026-59821not recordedLiteLLM: Custom Code Guardrails production endpoints bypass code safety checks1.82.0
CVE-2026-59822not recordedLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback1.84.0
CVE-2026-59823not recordedLiteLLM Proxy has server-side request forgery via the `user_config` request parameter1.83.9
CVE-2026-84377not recordedLiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters1.96.2
GHSA-69x8-hrgq-fjj8not recordedLiteLLM: Password hash exposure and pass-the-hash authentication bypass1.83.0
GHSA-g5ff-637f-6q2mnot recordedLiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`1.95.0
GHSA-hhww-mrg2-969hnot recordedLiteLLM vulnerable to reflected XSS in /sso/debug/callback1.85.0

Advisories with no recorded fix are listed first. CVE IDs link to NVD, GHSA IDs to GitHub and other IDs to OSV. A fixed advisory affects only versions below its fix; vet exits 1 only for advisories with no fix.

What it can do

  • It can make outbound network requests.

Capability tags come from the registry. Credenzo uses them to find dangerous combinations with your other servers.

Check how you run it

This page describes the public package. What matters is your setup: which version you pin, which secrets you pass, and which other servers sit next to it.

mcp-audit check

Badge for your README

mcp-audit31 fixed CVEs

Preview drawn by this page. The real badge is rendered by shields.io from this JSON and updates when the registry does.

[![mcp-audit](https://img.shields.io/endpoint?url=https://mcp-audit.dev/v1/badge/pypi/litellm.json)](https://mcp-audit.dev/servers/pypi/litellm/)