CVE-2026-30623
LiteLLM Remote Code Execution
Description
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.
INFO
Published Date :
July 15, 2026, 10:16 p.m.
Last Modified :
July 16, 2026, 2:16 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
Affected Products
The following products are affected by CVE-2026-30623
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | CRITICAL | 134c704f-9b21-4f2e-91b3-4a467353bcc0 |
Solution
- Update LiteLLM to the latest stable version.
- Review and validate all MCP server configurations.
- Sanitize any user-provided command or argument values.
- Implement stricter input validation for MCP configurations.
Public PoC/Exploit Available at Github
CVE-2026-30623 has a 6 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-30623.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-30623 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-30623
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Drop-in fix for the unpatched MCP STDIO command-injection flaw (CVE-2026-30623 family)
Python
MCP security scanner for financial AI systems — detects prompt injection, tool poisoning, and DORA/MiCA compliance gaps
Python
Static linter for MCP servers and configs. Every rule is pinned to a real CVE with a biting fixture.
ai-agents cve linter mcp model-context-protocol security static-analysis supply-chain
Python
The Project shares all information on MCP related CVE's published
mcp mcp-security mcp-cve
Drop-in Rust sidecar for MCP servers — scans tool calls for prompt injection, validates Ed25519 manifest signatures, blocks marketplace-poisoning vectors. <5ms p99 overhead. Defense against OX Security MCP advisory (10+ CVEs, April 2026).
anthropic built-in-mallorca claude ed25519 mcp mcp-security mcp-server model-context-protocol prompt-injection rust security sidecar signature supply-chain-security
Rust Dockerfile
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
ai-agent-security ai-agents ai-security awesome-list cybersecurity llm-security mcp-security prompt-injection supply-chain-security adversarial-attacks agent-security agentic-ai ai-attacks ai-safety cve incident-response owasp red-team security-research vulnerability
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-30623 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-30623 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jul. 16, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Added CWE CWE-77 Added SSVC {'id': 'CVE-2026-30623', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'yes'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-07-16T13:19:11.300119Z'} -
New CVE Received by [email protected]
Jul. 15, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'n/a', 'product': 'n/a', 'versions': [{'status': 'affected', 'version': 'n/a'}]}] Added Description 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. Added Reference https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026 Added Reference https://github.com/BerriAI/litellm Added Reference https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/