MCP open_url -> Arbitrary Android Intent

← Agentic AI (OWASP Agentic Top 10)

mcp_open_url_arbitrary_intent   HARD

Description

An MCP tool the agent can invoke (mobile_open_url) maps a model-supplied URL straight to Android startActivity() with no scheme allowlist, so a prompt-injected agent fires dangerous intents (tel:/sms:/content://) and reaches privileged, cross-app actions (Mobile MCP CVE-2026-35394 class).

How it works

An MCP tool the agent can invoke, mobile_open_url, takes a model-supplied URL and maps it straight to Android startActivity() with no scheme allowlist and no confirmation. Because a prompt-injected agent controls that argument, it can fire dangerous intents (tel:, sms:, content://, intent://) that reach privileged, cross-app actions such as dialing a premium line, reading a content provider, or launching an arbitrary intent on the user’s behalf (Mobile MCP CVE-2026-35394 class). The secure path allows only https and http, refuses every privileged scheme, and requires explicit user confirmation, so a model argument alone can never dispatch a privileged intent.

How to exercise it. DVMA is the harness - open this module from the home index and tap the demo action. The screen ships the malicious input and simulates the attacker (e.g. the companion app, crafted intent, or scanned payload) in-process, and the evidence panel prints the proof. The Tools (optional) and Attack inputs below are only needed to reproduce the exploit end-to-end on a real device.

Exploit steps

1. Set up. Build DVMA with a flavor that enables the Agentic AI (OWASP Agentic Top 10) category (e.g. --dart-define-from-file=config/flavors/dev.json) and run on an emulator/simulator you control. The demo needs no external tooling; for the optional on-device reproduction the relevant tools are: promptfoo, Burp Suite, MCP scanner, mitmproxy · Android: adb · iOS: xcrun simctl openurl.
2. Locate the target. From the home index, open MCP open_url -> Arbitrary Android Intent (mcp_open_url_arbitrary_intent). The How it works section above describes this module’s specific weakness; the screen states the intended-secure behavior and exposes the vulnerable action.
3. Exploit. Interact with the agent’s memory / tool / sub-agent channel, plant the malicious content, and confirm it influences a later action or is acted on without authentication.
4. Observe the evidence. Trigger the vulnerable action and read the evidence panel - it prints the concrete proof (leaked value, accepted replay, executed payload, or unauthorized result).
5. Contrast with the secure path. Run the module’s secure/hardened action (where provided) and confirm the same attack is rejected - this is what a correct implementation should do.
6. Map it back. Cross-reference the MASTG v2 test(s) MASTG-TEST-0026, MASTG-TEST-0027 for the canonical procedure and remediation.

Tools (optional)

• promptfoo
• Burp Suite
• MCP scanner
• mitmproxy

Android

• adb

iOS

• xcrun simctl openurl

garak / promptfoo / MCP scanner test the LLM or MCP endpoint behind the app, not the app binary. Point them at the backend model API (find it with mitmproxy / Burp Suite) or a local on-device model server; the in-app demo already exercises the same prompt path.

Attack inputs

Payloads/artifacts you author for the on-device attack. The demo already ships and simulates these in-process (e.g. the malicious companion app / crafted intent is emulated inside the screen), so you only need to craft them to reproduce the exploit on a real device:

• crafted prompt

Real-world references

Concrete public disclosures that match this vulnerability class:

• CVE-2026-35394 / GHSA-5qhv-x9j4-c3vm (Mobile MCP arbitrary Android intent via mobile_open_url)