---
cve: "CVE-2026-88755"
severity: "HIGH"
cvss: 7.8
epss: "0.2%"
vendor: "n/a"
kev: false
exploited: false
published: "2026-10-16 15:17:33"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-10-25T19:05:52+01:00"
---

# CVE-2026-88755

> 7.8 HIGH · 🧪 PoC

## Beschreibung

Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace configuration, possibly allowing attackers to execute arbitrary code via opening a crafted repository.

## CNA-Record (Kanon, cvelistV5)

- CNA: **mitre**
- State: PUBLISHED
- Stand: 2026-10-16 19:06:26

## CISA-Anreicherung (vulnrichment/ADP)

- CISA-SSVC (Coordinator, v2.0.3):
  - Exploitation: **poc**
  - Automatable: **no**
  - Technical Impact: **total**

## CVSS-Vektor

```
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Lokal | good |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |
| UI Interaktion | Erforderlich | good |
| S Scope | Unverändert | good |
| C Vertraulichkeit | Hoch | bad |
| I Integrität | Hoch | bad |
| A Verfügbarkeit | Hoch | bad |

## Schwachstellen-Klasse

- **CWE-78** — Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
  The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
- **CWE-200** — Exposure of Sensitive Information to an Unauthorized Actor
  The product exposes sensitive information to an actor that is not explicitly authorized to have access to that information.
- **CWE-284** — Improper Access Control
  The product does not restrict or incorrectly restricts access to a resource from an unauthorized actor.
- **CWE-863** — Incorrect Authorization
  The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.

## Angriffsmuster (CAPEC)

- [CAPEC-6 — Argument Injection](https://capec.mitre.org/data/definitions/6.html) _(Severity: High)_
- [CAPEC-15 — Command Delimiters](https://capec.mitre.org/data/definitions/15.html) _(Severity: High)_
- [CAPEC-43 — Exploiting Multiple Input Interpretation Layers](https://capec.mitre.org/data/definitions/43.html) _(Severity: High)_
- [CAPEC-88 — OS Command Injection](https://capec.mitre.org/data/definitions/88.html) _(Severity: High)_
- [CAPEC-108 — Command Line Execution through SQL Injection](https://capec.mitre.org/data/definitions/108.html) _(Severity: Very High)_

## Referenzen

- <http://zai.com>
- <http://zcode.com>
- <https://gist.github.com/lkloliver/aac8dcf8a53fc4b3c1b0a5dfbf36ef68>
- <https://github.com/lkloliver/poc/tree/main/CVE-2026-88755>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/sicherheitsluecken/cve-2026-88755/) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI WID (CSAF)_