Technology · PyPI
litellm (PyPI) vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 45 vulnerabilities in litellm (PyPI): 0 in the last 7 days and 6 in the last 90 days, 8 of them critical and 3 exploited in the wild. The most recent, LiteLLM arbitrary local file read via vertex_ai_credentials, was published on 27 October 2026. 3 vulnerabilities in the last four weeks, up 200% on the four before (1). 1 critical against 0.
- Last 7 days
- 0
- Last 90 days
- 6
- Critical, all time
- 8
- Exploited in the wild
- 3
About litellm (PyPI)
Python library providing unified interface to multiple large language models.
Latest litellm (PyPI) vulnerabilities
- LiteLLM arbitrary local file read via vertex_ai_credentialshighCVSS 8.1
- LiteLLM reflected XSS in SSO debug callback endpointmediumCVSS 6.8
- CVE-2026-114612: LiteLLM proxy authentication bypass via reused crypto contextcriticalCVSS 9.9EPSS 0.3%
- CVE-2026-59823: LiteLLM Proxy server-side request forgery in user_config parametermediumCVSS 4EPSS 0.4%
- CVE-2026-84377: LiteLLM proxy request parameter injection leading to credential exposuremediumCVSS 6.5EPSS 0.5%
- CVE-2026-37004: BerriAI LiteLLM server-side template injection in prompts endpointcriticalCVSS 9.8EPSS 0.8%
- CVE-2026-59822: BerriAI LiteLLM authentication bypass in MCP endpointcriticalexploited in the wildCVSS 4EPSS 0.8%
- CVE-2026-59821: BerriAI LiteLLM code injection in Custom Code GuardrailsmediumCVSS 4EPSS 0.9%
- CVE-2026-59820: BerriAI LiteLLM path traversal in Skills archive extractionmediumCVSS 4EPSS 0.6%
- CVE-2026-59819: BerriAI LiteLLM local file read in health test_connection endpointmediumCVSS 4EPSS 0.6%
- CVE-2025-0330: PYSEC-2026-1543 - LiteLLM Has a Leakage of Langfuse API KeyslowCVSS 3EPSS 0.6%
- CVE-2025-0628: PYSEC-2026-1546 - LiteLLM Has an Improper Authorization VulnerabilitylowCVSS 3EPSS 0.3%
- CVE-2024-9606: PYSEC-2026-1548 - LiteLLM Reveals Portion of API Key via a Logging FilelowCVSS 3EPSS 0.8%
- CVE-2024-8984: PYSEC-2026-1545 - LiteLLM Vulnerable to Denial of Service (DoS) via Crafted HTTP RequestlowCVSS 3EPSS 0.8%
- CVE-2024-6825: PYSEC-2026-1541 - LiteLLM Vulnerable to Remote Code Execution (RCE)lowCVSS 3EPSS 1.7%
- CVE-2024-10188: PYSEC-2026-1549 - LiteLLM Vulnerable to Denial of Service (DoS)lowCVSS 3EPSS 0.6%
- CVE-2024-6587: PYSEC-2026-1547 - LiteLLM Server-Side Request Forgery (SSRF) vulnerabilitylowCVSS 3EPSS 35.3%
- CVE-2024-5710: PYSEC-2026-1551 - litellm vulnerable to improper access control in team managementlowCVSS 3.1EPSS 0.4%
- CVE-2024-5225: PYSEC-2026-1550 - SQL injection in litellmlowCVSS 3EPSS 0.4%
- CVE-2024-4890: PYSEC-2026-1544 - SQL injection in litellmlowCVSS 3EPSS 0.6%
- CVE-2024-4888: PYSEC-2026-1540 - Arbitrary file deletion in litellmlowCVSS 3EPSS 0.6%
- CVE-2024-4264: PYSEC-2026-1542 - litellm passes untrusted data to `eval` function without sanitizationlowCVSS 3.1EPSS 0.9%
- CVE-2024-5751: PYSEC-2026-389 - litellm vulnerable to remote code execution based on using eval unsafelylowCVSS 3EPSS 0.9%
- CVE-2026-49468: BerriAI LiteLLM authentication bypass via Host header injectioncriticalCVSS 4EPSS 0.8%
- CVE-2026-12799: BerriAI LiteLLM improper authorization in ui_view_users functionmediumCVSS 4.3EPSS 0.4%
Most severe litellm (PyPI) vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-42208: BerriAI LiteLLM SQL injection in Proxy API key verificationcriticalexploited in the wildCVSS 9.8EPSS 5.8%
- CVE-2026-42271: BerriAI LiteLLM OS command injection in MCP test endpointscriticalexploited in the wildCVSS 8.8EPSS 12.8%
- CVE-2026-59822: BerriAI LiteLLM authentication bypass in MCP endpointcriticalexploited in the wildCVSS 4EPSS 0.8%
- CVE-2026-114612: LiteLLM proxy authentication bypass via reused crypto contextcriticalCVSS 9.9EPSS 0.3%
- CVE-2024-2952: BerriAI LiteLLM SSTI in completions endpointcriticalCVSS 9.8EPSS 1.3%
- CVE-2026-37004: BerriAI LiteLLM server-side template injection in prompts endpointcriticalCVSS 9.8EPSS 0.8%
- CVE-2026-35030: BerriAI LiteLLM authentication bypass via OIDC cache key collisioncriticalCVSS 9.1EPSS 0.9%
- CVE-2026-49468: BerriAI LiteLLM authentication bypass via Host header injectioncriticalCVSS 4EPSS 0.8%
- CVE-2026-35029: BerriAI LiteLLM incorrect authorization in config update endpointhighCVSS 8.8EPSS 4.0%
- CVE-2026-40217: BerriAI LiteLLM remote code execution in guardrails componenthighCVSS 8.8EPSS 3.4%
Vulnerabilities per week
3 vulnerabilities in the last four weeks, up 200% on the four before (1). 1 critical against 0. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 1 | 1 | |
| 31 Aug 2026 | 1 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 1 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 0 | 0 | |
| 12 Oct 2026 | 0 | 0 | |
| 19 Oct 2026 | 1 | 1 | |
| 26 Oct 2026 | 2 | 0 | |
| 2 Nov 2026 | 0 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many litellm (PyPI) vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/technologies/pypi-litellm)<a href="https://junglewise.ai/threats/technologies/pypi-litellm"><img src="https://junglewise.ai/threats/technologies/pypi-litellm/badge.svg" alt="litellm (PyPI) vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/pypi-litellm.json, and this page as text at https://junglewise.ai/threats/technologies/pypi-litellm.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "litellm (PyPI) vulnerabilities", https://junglewise.ai/threats/technologies/pypi-litellm, 13 November 2026.