Cyber Resilience

CVE-2026-35394

Mobilenexthq Mobile Mcp ≤ 0.0.50

Public PoC
Published
06 April 2026
Modified
24 July 2026
Patch / advisory
CVSS Score v3.1 8.3
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:H
EPSS Score 0.0039 32th percentile
Risk Priority 61 floored blend · peak EPSS

Summary

CVE-2026-35394 is a high-severity Improper Authorization in Handler for Custom URL Scheme (CWE-939) vulnerability in Mobilenexthq Mobile Mcp. Its CVSS base score is 8.3 (High).

Operationally, ranked at the 32th percentile by exploit likelihood (below the median); 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 AC-3 (Access Enforcement) and AC-6 (Least Privilege) — 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-2026-35394 affects Mobile Next, an MCP server for mobile development and automation, specifically the mobile_open_url tool in the mobile-mcp component prior to version 0.0.50. The vulnerability stems from passing user-supplied URLs directly to Android's intent system without scheme validation, enabling the execution of arbitrary Android intents. This issue, classified under CWE-939 (Improper Authorization in Handler for Custom URL Scheme), carries a CVSS v3.1 base score of 8.3 (AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:H).

An attacker can exploit this vulnerability remotely over the network with low complexity and no required privileges, but it necessitates user interaction, such as tricking a user into invoking the mobile_open_url tool with a malicious URL. Successful exploitation allows the execution of arbitrary Android intents, potentially leading to actions like dialing USSD codes, initiating phone calls, sending SMS messages, or accessing content providers, resulting in high integrity and availability impacts alongside low confidentiality impact.

The GitHub security advisory for mobile-next/mobile-mcp (GHSA-5qhv-x9j4-c3vm) confirms the vulnerability is fixed in version 0.0.50, recommending users upgrade to this or later versions to mitigate the issue. No additional workarounds are specified in the provided references.

EU & UK References

Vulnerability Data

Mobile Next is an MCP server for mobile development and automation. Prior to 0.0.50, the mobile_open_url tool in mobile-mcp passes user-supplied URLs directly to Android's intent system without any scheme validation, allowing execution of arbitrary Android intents, including USSD codes,…

more

phone calls, SMS messages, and content provider access. This vulnerability is fixed in 0.0.50.

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

CVE-2026-33989Same product: Mobilenexthq Mobile Mcp
CVE-2026-26123Shared CWE-939
CVE-2026-53407Shared CWE-939
CVE-2025-41408Shared CWE-939
CVE-2026-1046Shared CWE-939
CVE-2025-67739Shared CWE-939
CVE-2024-54125Shared CWE-939
CVE-2025-5020Shared CWE-939
CVE-2024-45203Shared CWE-939
CVE-2024-54014Shared CWE-939

Affected Assets

mobilenexthq
mobile mcp
≤ 0.0.50

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Access enforcement directly stops unauthorized actors from invoking the custom URL handler by requiring approved authorizations for that entry point.

Least privilege limits the authorizations granted to the handler, reducing the chance that any actor can invoke it without restriction.

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.AA-05 mostly match
prevents

Defining, enforcing, and reviewing access permissions directly addresses the missing authorization checks for custom URL scheme handlers.

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.

finds

Security testing can discover missing authorization checks, but does not itself implement the required controls.

prevents

Enforces explicit authorization checks on which actors may invoke handlers, directly addressing the missing restriction on custom-URL-scheme access.

prevents

High-level access-control policy provides governance context but does not prescribe the technical authorization logic needed for URL-scheme handlers.

prevents

Requires security requirements that define which callers are permitted to trigger custom URL handlers, mitigating the authorization gap.

prevents

Mandates secure coding practices that include proper authorization checks before executing actions triggered by custom URL schemes.

References