# CVE-2026-30623 > As of 2026-07-16, CVE-2026-30623 is a CRITICAL-severity vulnerability, CVSS v3.1 9.8, EPSS 4.9% (92.0th percentile). Threadlinqs Intelligence links 1 tracked threat campaign to CVE-2026-30623, most recently “Four Chained Exploit Paths in LiteLLM Proxy (Pre-Auth RCE to Master Key Exfiltration) — STAR Labs Pwn2Own Research”. **Last updated:** 2026-07-16 ## What is CVE-2026-30623? LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality. The application allows users to add MCP servers via a JSON configuration specifying arbitrary command and args values. LiteLLM executes these values on the host without validation, enabling attackers to run arbitrary operating system commands. Successful exploitation may result in remote code execution with the privileges of the LiteLLM process. The record classifies CVE-2026-30623 under weakness class [CWE-77](https://intel.threadlinqs.com/cwe/CWE-77). Its CVSS v3 base vector states that the flaw is reachable remotely over the network, needs no prior authentication, needs no user interaction, and has high impact on confidentiality, integrity, availability. The identifier was first published 106 days ago. ## Severity and exploitation probability - **CVSS v3.1 base score:** 9.8 — CRITICAL (`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`) - **EPSS (FIRST):** 4.9% probability of exploitation in the next 30 days, higher than 92.0% of all scored CVEs - **CISA KEV:** Not listed in the CISA Known Exploited Vulnerabilities catalog - **Threadlinqs priority:** 10/10 — a Threadlinqs composite of the CVSS base score, the EPSS percentile and public exploit availability - **Published:** 2026-07-15, last modified 2026-07-16 ## Is CVE-2026-30623 being exploited? Weaponised exploit code for CVE-2026-30623 is publicly available. 1 public proof-of-concept repository is tracked for this identifier. A ProjectDiscovery Nuclei detection template exists (`http/cves/2026/CVE-2026-30623.yaml`). It currently carries a trending score of 46 in the Threadlinqs vulnerability feed. - [csinexus/mcpshield](https://github.com/csinexus/mcpshield) (github) ## Affected products and versions No affected-product or package list has been recorded for CVE-2026-30623 in the tracked sources. The vendor advisory and the references below are the authoritative statement of what is affected. ## How to fix CVE-2026-30623 No vendor patch reference has been recorded for CVE-2026-30623 in the tracked sources. Follow the references below for a fix, and treat any affected deployment as exposed until the vendor states otherwise. ## Threat activity tracking CVE-2026-30623 1 tracked threat in the Threadlinqs corpus references CVE-2026-30623, either in the campaign’s CVE list or as an indicator on the campaign record. - [Four Chained Exploit Paths in LiteLLM Proxy (Pre-Auth RCE to Master Key Exfiltration) — STAR Labs Pwn2Own Research](https://intel.threadlinqs.com/threat/TL-2026-1540) — CRITICAL · 2026-07-19 ## Sources Enriched from CVE.org, NVD, FIRST EPSS, public proof-of-concept repositories, ProjectDiscovery Nuclei. Last verified by Threadlinqs on 2026-10-10. This product uses the NVD API but is not endorsed or certified by the NVD. **Other references** - [github.com](https://github.com/BerriAI/litellm) - [ox.security](https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/) - [docs.litellm.ai](https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026) Canonical: https://intel.threadlinqs.com/cve/CVE-2026-30623 Full detection coverage and IOCs for threats exploiting CVE-2026-30623 via the Threadlinqs MCP server (Purple tier): https://intel.threadlinqs.com/mcp