---
cve: "CVE-2026-26015"
severity: "CRITICAL"
cvss: 10.0
epss: "1.2%"
vendor: "arc53"
kev: false
exploited: false
published: "2026-04-29 18:16:03"
tags: [cve, security, critical]
source: tsecurity.de CVE-Dossier
exported: "2026-11-09T11:34:29+01:00"
---

# CVE-2026-26015

> 10.0 CRITICAL · 🧪 PoC

## Beschreibung

DocsGPT is a GPT-powered chat for documentation. From version 0.15.0 to before version 0.16.0, an attacker accessing both the official DocsGPT website or any local and public deployment, can craft a malicious payload bypassing the "MCP test" behavior to achieve arbitrary remote code execution (RCE). This issue has been patched in version 0.16.0.

## CNA-Record (Kanon, cvelistV5)

- CNA: **GitHub_M**
- State: PUBLISHED
- Stand: 2026-05-06 19:43:48
- CNA-CVSS: **10.0** (`CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H`)

## CISA-Anreicherung (vulnrichment/ADP)

- CISA-SSVC (Coordinator, v2.0.3):
  - Exploitation: **poc**
  - Automatable: **yes**
  - Technical Impact: **total**

## CVSS-Vektor

```
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |
| UI Interaktion | Keine | bad |

## Schwachstellen-Klasse

- **CWE-77** — Improper Neutralization of Special Elements used in a Command (Command Injection)
  The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component.

## Angriffsmuster (CAPEC)

- [CAPEC-15 — Command Delimiters](https://capec.mitre.org/data/definitions/15.html) _(Severity: High)_
- [CAPEC-40 — Manipulating Writeable Terminal Devices](https://capec.mitre.org/data/definitions/40.html) _(Severity: Very High)_
- [CAPEC-43 — Exploiting Multiple Input Interpretation Layers](https://capec.mitre.org/data/definitions/43.html) _(Severity: High)_
- [CAPEC-75 — Manipulating Writeable Configuration Files](https://capec.mitre.org/data/definitions/75.html) _(Severity: Very High)_
- [CAPEC-76 — Manipulating Web Input to File System Calls](https://capec.mitre.org/data/definitions/76.html) _(Severity: Very High)_
- [CAPEC-136 — LDAP Injection](https://capec.mitre.org/data/definitions/136.html) _(Severity: High)_
- [CAPEC-183 — IMAP/SMTP Command Injection](https://capec.mitre.org/data/definitions/183.html) _(Severity: Medium)_
- [CAPEC-248 — Command Injection](https://capec.mitre.org/data/definitions/248.html) _(Severity: High)_

## Patch verfügbar (OSV)

- 72b3d944534244baed4727824f30c55bc3d82495 (Commit)

## Referenzen

- <https://github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74>
- <https://github.com/arc53/DocsGPT/releases/tag/0.16.0>
- <https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/>
- <https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp/>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/sicherheitsluecken/cve-2026-26015/) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI WID (CSAF)_