# litellm (PyPI) vulnerabilities Source: https://junglewise.ai/threats/technologies/pypi-litellm Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 13 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/technologies/pypi-litellm.json License: CC BY 4.0 with a link back 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. ## Counts - Last 7 days: 0 - Last 30 days: 3 - Last 90 days: 6 - All time: 45 (8 critical, 3 exploited in the wild) ## 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_credentials](https://junglewise.ai/threats/litellm-internal-user-viewer-arbitrary-local-file-read-via-vertex-ai-649a7475) (high, CVSS 8.1, published 27 Oct 2026) - [LiteLLM reflected XSS in SSO debug callback endpoint](https://junglewise.ai/threats/litellm-vulnerable-to-reflected-xss-in-sso-debug-callback-38154651) (medium, CVSS 6.8, published 27 Oct 2026) - [CVE-2026-114612: LiteLLM proxy authentication bypass via reused crypto context](https://junglewise.ai/threats/cve-2026-114612-litellm-is-a-proxy-server-ai-gateway-to-call-llm-apis-in-openai) (critical, CVSS 9.9, published 22 Oct 2026) - [CVE-2026-59823: LiteLLM Proxy server-side request forgery in user_config parameter](https://junglewise.ai/threats/cve-2026-59823-litellm-proxy-server-side-request-forgery-in-user-config) (medium, CVSS 4, published 16 Sep 2026) - [CVE-2026-84377: LiteLLM proxy request parameter injection leading to credential exposure](https://junglewise.ai/threats/cve-2026-84377-litellm-proxy-request-parameter-injection-leading-to-credential) (medium, CVSS 6.5, published 2 Sep 2026) - [CVE-2026-37004: BerriAI LiteLLM server-side template injection in prompts endpoint](https://junglewise.ai/threats/cve-2026-37004-berriai-litellm-server-side-template-injection-in-prompts) (critical, CVSS 9.8, published 27 Aug 2026) - [CVE-2026-59822: BerriAI LiteLLM authentication bypass in MCP endpoint](https://junglewise.ai/threats/cve-2026-59822-berriai-litellm-authentication-bypass-in-mcp-endpoint) (critical, exploited in the wild, CVSS 4, published 8 Jul 2026) - [CVE-2026-59821: BerriAI LiteLLM code injection in Custom Code Guardrails](https://junglewise.ai/threats/cve-2026-59821-berriai-litellm-code-injection-in-custom-code-guardrails) (medium, CVSS 4, published 8 Jul 2026) - [CVE-2026-59820: BerriAI LiteLLM path traversal in Skills archive extraction](https://junglewise.ai/threats/cve-2026-59820-berriai-litellm-path-traversal-in-skills-archive-extraction) (medium, CVSS 4, published 8 Jul 2026) - [CVE-2026-59819: BerriAI LiteLLM local file read in health test_connection endpoint](https://junglewise.ai/threats/cve-2026-59819-berriai-litellm-local-file-read-in-health-test-connection) (medium, CVSS 4, published 8 Jul 2026) - [CVE-2025-0330: PYSEC-2026-1543 - LiteLLM Has a Leakage of Langfuse API Keys](https://junglewise.ai/threats/cve-2025-0330-litellm-has-a-leakage-of-langfuse-api-keys) (low, CVSS 3, published 7 Jul 2026) - [CVE-2025-0628: PYSEC-2026-1546 - LiteLLM Has an Improper Authorization Vulnerability](https://junglewise.ai/threats/cve-2025-0628-litellm-has-an-improper-authorization-vulnerability) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-9606: PYSEC-2026-1548 - LiteLLM Reveals Portion of API Key via a Logging File](https://junglewise.ai/threats/cve-2024-9606-litellm-reveals-portion-of-api-key-via-a-logging-file) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-8984: PYSEC-2026-1545 - LiteLLM Vulnerable to Denial of Service (DoS) via Crafted HTTP Request](https://junglewise.ai/threats/cve-2024-8984-litellm-vulnerable-to-denial-of-service-dos-via-crafted-http) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-6825: PYSEC-2026-1541 - LiteLLM Vulnerable to Remote Code Execution (RCE)](https://junglewise.ai/threats/cve-2024-6825-litellm-vulnerable-to-remote-code-execution-rce) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-10188: PYSEC-2026-1549 - LiteLLM Vulnerable to Denial of Service (DoS)](https://junglewise.ai/threats/cve-2024-10188-litellm-vulnerable-to-denial-of-service-dos) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-6587: PYSEC-2026-1547 - LiteLLM Server-Side Request Forgery (SSRF) vulnerability](https://junglewise.ai/threats/cve-2024-6587-litellm-server-side-request-forgery-ssrf-vulnerability) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-5710: PYSEC-2026-1551 - litellm vulnerable to improper access control in team management](https://junglewise.ai/threats/cve-2024-5710-litellm-vulnerable-to-improper-access-control-in-team-management) (low, CVSS 3.1, published 7 Jul 2026) - [CVE-2024-5225: PYSEC-2026-1550 - SQL injection in litellm](https://junglewise.ai/threats/cve-2024-5225-sql-injection-in-litellm) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-4890: PYSEC-2026-1544 - SQL injection in litellm](https://junglewise.ai/threats/cve-2024-4890-sql-injection-in-litellm) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-4888: PYSEC-2026-1540 - Arbitrary file deletion in litellm](https://junglewise.ai/threats/cve-2024-4888-arbitrary-file-deletion-in-litellm) (low, CVSS 3, published 7 Jul 2026) - [CVE-2024-4264: PYSEC-2026-1542 - litellm passes untrusted data to `eval` function without sanitization](https://junglewise.ai/threats/cve-2024-4264-litellm-passes-untrusted-data-to-eval-function-without) (low, CVSS 3.1, published 7 Jul 2026) - [CVE-2024-5751: PYSEC-2026-389 - litellm vulnerable to remote code execution based on using eval unsafely](https://junglewise.ai/threats/cve-2024-5751-litellm-vulnerable-to-remote-code-execution-based-on-using-eval) (low, CVSS 3, published 29 Jun 2026) - [CVE-2026-49468: BerriAI LiteLLM authentication bypass via Host header injection](https://junglewise.ai/threats/cve-2026-49468-berriai-litellm-authentication-bypass-via-host-header-injection) (critical, CVSS 4, published 22 Jun 2026) - [CVE-2026-12799: BerriAI LiteLLM improper authorization in ui_view_users function](https://junglewise.ai/threats/cve-2026-12799-berriai-litellm-improper-authorization-in-ui-view-users-function) (medium, CVSS 4.3, published 21 Jun 2026) ## Most severe litellm (PyPI) vulnerabilities - [CVE-2026-42208: BerriAI LiteLLM SQL injection in Proxy API key verification](https://junglewise.ai/threats/cve-2026-42208-berriai-litellm-sql-injection-in-proxy-api-key-verification) (critical, exploited in the wild, CVSS 9.8, published 8 May 2026) - [CVE-2026-42271: BerriAI LiteLLM OS command injection in MCP test endpoints](https://junglewise.ai/threats/cve-2026-42271-berriai-litellm-os-command-injection-in-mcp-test-endpoints) (critical, exploited in the wild, CVSS 8.8, published 8 May 2026) - [CVE-2026-59822: BerriAI LiteLLM authentication bypass in MCP endpoint](https://junglewise.ai/threats/cve-2026-59822-berriai-litellm-authentication-bypass-in-mcp-endpoint) (critical, exploited in the wild, CVSS 4, published 8 Jul 2026) - [CVE-2026-114612: LiteLLM proxy authentication bypass via reused crypto context](https://junglewise.ai/threats/cve-2026-114612-litellm-is-a-proxy-server-ai-gateway-to-call-llm-apis-in-openai) (critical, CVSS 9.9, published 22 Oct 2026) - [CVE-2024-2952: BerriAI LiteLLM SSTI in completions endpoint](https://junglewise.ai/threats/cve-2024-2952-berriai-litellm-ssti-in-completions-endpoint) (critical, CVSS 9.8, published 10 Apr 2024) - [CVE-2026-37004: BerriAI LiteLLM server-side template injection in prompts endpoint](https://junglewise.ai/threats/cve-2026-37004-berriai-litellm-server-side-template-injection-in-prompts) (critical, CVSS 9.8, published 27 Aug 2026) - [CVE-2026-35030: BerriAI LiteLLM authentication bypass via OIDC cache key collision](https://junglewise.ai/threats/cve-2026-35030-berriai-litellm-authentication-bypass-via-oidc-cache-key) (critical, CVSS 9.1, published 6 Apr 2026) - [CVE-2026-49468: BerriAI LiteLLM authentication bypass via Host header injection](https://junglewise.ai/threats/cve-2026-49468-berriai-litellm-authentication-bypass-via-host-header-injection) (critical, CVSS 4, published 22 Jun 2026) - [CVE-2026-35029: BerriAI LiteLLM incorrect authorization in config update endpoint](https://junglewise.ai/threats/cve-2026-35029-berriai-litellm-incorrect-authorization-in-config-update-endpoint) (high, CVSS 8.8, published 6 Apr 2026) - [CVE-2026-40217: BerriAI LiteLLM remote code execution in guardrails component](https://junglewise.ai/threats/cve-2026-40217-berriai-litellm-remote-code-execution-in-guardrails-component) (high, CVSS 8.8, published 10 Apr 2026) ## Vulnerabilities per week 3 vulnerabilities in the last four weeks, up 200% on the four before (1). 1 critical against 0. | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 1 | 1 | 0 | | 31 Aug 2026 | 1 | 0 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 1 | 0 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 0 | 0 | 0 | | 5 Oct 2026 | 0 | 0 | 0 | | 12 Oct 2026 | 0 | 0 | 0 | | 19 Oct 2026 | 1 | 1 | 0 | | 26 Oct 2026 | 2 | 0 | 0 | | 2 Nov 2026 | 0 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## Other PyPI technologies - [tensorflow (PyPI)](https://junglewise.ai/threats/technologies/pypi-tensorflow): 435 vulnerabilities - [tensorflow-cpu (PyPI)](https://junglewise.ai/threats/technologies/tensorflow-cpu): 430 vulnerabilities - [tensorflow-gpu (PyPI)](https://junglewise.ai/threats/technologies/tensorflow-gpu): 427 vulnerabilities - [open-webui (PyPI)](https://junglewise.ai/threats/technologies/open-webui): 177 vulnerabilities - [Django (PyPI)](https://junglewise.ai/threats/technologies/django): 173 vulnerabilities - [apache-airflow (PyPI)](https://junglewise.ai/threats/technologies/apache-airflow): 159 vulnerabilities - [pillow (PyPI)](https://junglewise.ai/threats/technologies/pillow): 125 vulnerabilities - [praisonai (PyPI)](https://junglewise.ai/threats/technologies/pypi-praisonai): 120 vulnerabilities - [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm): 117 vulnerabilities - [plone (PyPI)](https://junglewise.ai/threats/technologies/pypi-plone): 101 vulnerabilities - [mlflow (PyPI)](https://junglewise.ai/threats/technologies/mlflow): 88 vulnerabilities - [picklescan (PyPI)](https://junglewise.ai/threats/technologies/picklescan): 86 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "litellm (PyPI) vulnerabilities", https://junglewise.ai/threats/technologies/pypi-litellm, 13 November 2026.