Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:HSummary
CVE-2026-23523 is a critical-severity Code Injection (CWE-94) vulnerability in Openagentplatform Dive. Its CVSS base score is 9.6 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 7% 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 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.
CVE-2026-23523 is a high-severity vulnerability in Dive, an open-source MCP Host Desktop Application designed to enable integration with function-calling large language models (LLMs). In versions prior to 0.13.0, the application fails to enforce sufficient user confirmation when processing crafted deeplinks, allowing the installation of an attacker-controlled MCP server configuration. This flaw, classified under CWE-94 (Code Injection), carries a CVSS v3.1 base score of 9.6 (AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H).
A remote attacker without privileges can exploit this issue by distributing a malicious deeplink, typically via social engineering to induce user interaction such as clicking a link. Upon processing, the deeplink installs the attacker's MCP server configuration, enabling arbitrary local command execution on the victim's machine. This grants the attacker high-impact control over confidentiality, integrity, and availability, with a changed scope due to the privilege escalation from network to local system access.
The vulnerability is addressed in Dive version 0.13.0. Security practitioners should update to this version immediately. Additional details are available in the GitHub security advisory (GHSA-pjj5-f3wm-f9m8) and the patching commit (a5162ac9eff366d8ea1215b8a47139a81a55a779).
This issue holds relevance for AI/ML deployments involving LLM integrations, as Dive facilitates function-calling workflows that could expose desktop environments to remote compromise. No public evidence of real-world exploitation has been reported as of the CVE publication on 2026-01-16.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-3125
Vulnerability Data
Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. Prior to 0.13.0, crafted deeplink can install an attacker-controlled MCP server configuration without sufficient user confirmation and can lead to arbitrary local command execution on the…
more
victim’s machine. This vulnerability is fixed in 0.13.0.
- 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: llms, mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.1
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation finds code paths that accept and execute externally influenced strings.
Input validation directly stops untrusted data from being used to construct executable code without neutralization.
Least privilege limits the damage an injected code fragment can perform once executed.
Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.PS-06's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).
PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.
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.
Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.
Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.