CVE-2026-2131
Published: 08 February 2026
Summary
CVE-2026-2131 is a medium-severity Command Injection (CWE-77) vulnerability in Xixianliang Harmonyos Mcp Server. Its CVSS base score is 6.3 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Unix Shell (T1059.004); ranked in the top 40.6% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
The strongest mitigations our analysis identified are NIST 800-53 SI-10 (Information Input Validation) and SI-2 (Flaw Remediation).
Threat & Defense at a Glance
Threat & Defense Details
Mitigating Controls (NIST 800-53 r5)AI
Directly prevents OS command injection by requiring validation and sanitization of the untrusted text argument in the input_text function.
Remediates the specific flaw in HarmonyOS-mcp-server 0.1.0 by identifying, reporting, and correcting the command injection vulnerability.
Enforces restrictions such as format and content checks on the text input at system boundaries to block command injection payloads.
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
OS command injection directly enables arbitrary Unix shell command execution (T1059.004) via exploitation of the remote service (T1210).
NVD Description
A vulnerability was identified in XixianLiang HarmonyOS-mcp-server 0.1.0. This vulnerability affects the function input_text. The manipulation of the argument text leads to os command injection. Remote exploitation of the attack is possible. The exploit is publicly available and might be…
more
used.
Deeper analysisAI
CVE-2026-2131, published on 2026-02-08, is an OS command injection vulnerability in XixianLiang HarmonyOS-mcp-server version 0.1.0. The issue affects the input_text function, where manipulation of the text argument enables command injection. It carries a CVSS v3.1 base score of 6.3 (AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L) and maps to CWEs-77 and CWE-78.
Remote exploitation is possible by an attacker possessing low privileges. Successful attacks allow limited impacts on confidentiality, integrity, and availability via injected OS commands.
Advisories and further details, including a public exploit, are documented in references such as https://github.com/scanleale/MCP_sec/blob/main/HarmonyOS-mcp-server%20RCE%20vulnerability.md, https://vuldb.com/?ctiid.344766, https://vuldb.com/?id.344766, and https://vuldb.com/?submit.747209. The exploit is publicly available and might be used.
The vulnerability description notes that remote exploitation is feasible, with the public exploit increasing potential for real-world abuse.
Details
- CWE(s)
Affected Products
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp