Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:HCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-30624 is a high-severity Command Injection (CWE-77) vulnerability in Agent-Zero Agent-Zero. Its CVSS base score is 8.6 (High).
Operationally, ranked at the 47th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
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 map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
Agent Zero version 0.9.8 is affected by CVE-2026-30624, a remote code execution vulnerability in its External MCP Servers configuration feature. The application permits users to specify MCP servers through a JSON configuration that includes arbitrary command and args values. These values are executed by the application upon applying the configuration, lacking adequate validation or restrictions, which enables attackers to supply malicious configurations for executing arbitrary operating system commands. This issue, published on 2026-04-15, carries a CVSS v3.1 base score of 8.6 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H) and is associated with CWE-77 (Command Injection).
The vulnerability can be exploited remotely by unauthenticated attackers over the network with low complexity and no user interaction required. By providing a crafted MCP server configuration, an attacker can trigger execution of arbitrary OS commands with the privileges of the Agent Zero process, potentially leading to remote code execution. The impact includes low confidentiality and integrity effects alongside high availability disruption, allowing control over the host system depending on the process context.
For mitigation details, refer to the advisory at https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/, which covers RCE vulnerabilities in the MCP supply chain across the AI ecosystem.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-22943
Vulnerability Data
Agent Zero 0.9.8 contains a remote code execution vulnerability in its External MCP Servers configuration feature. The application allows users to define MCP servers using a JSON configuration containing arbitrary command and args values. These values are executed by the…
more
application when the configuration is applied without sufficient validation or restriction. An attacker may supply a malicious MCP configuration to execute arbitrary operating system commands, potentially resulting in remote code execution with the privileges of the Agent Zero process.
- CWE(s)
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
Related Threats
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover command-construction flaws before deployment.
Input validation directly stops construction of commands from untrusted data containing special elements.
Secure engineering principles include proper neutralization and safe command construction practices.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing in development catches command-injection vulnerabilities before release.
Secure coding standards require proper escaping and parameterization of commands, directly eliminating CWE-77.
Hardening callouts derived
DISA STIG baselines are authored against specific weaknesses. Where this CVE cites a broad weakness class, the mapping is not asserted at that abstraction (owner ruling, 2026-09-25: grade only at Base and below), so no rule is shown here rather than a rule shown against the wrong grain.
- No fine-grained STIG row for CWE-77, a class-level weakness, and none of its children carries one either.