Is iphone-use safe to use?

iphone-use scores 83/100 (grade B) on the Canopii Trust Index — good, minor gaps. It passes 11 of the 21 security controls that apply to it, with no confirmed security failures.

How reliable is the security score for iphone-use?

We could evaluate 82% of the controls that apply to iphone-use. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.

How was iphone-use scored?

Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.

iphone-use MCP Server Security Report

leeguooooo/iphone-use

响应快省Token， Let AI agents (Claude Code, Codex, any MCP client) drive a real iPhone · 让 AI agent 操作真实 iPhone：读屏、点击、输入、滑动，USB 或 Wi-Fi，自有 XCTest runner，可回放的 App flow。Open source, self-hosted on macOS.

83B

Security Trust Score

Grade B · Moderate posture

Tier 1 · Public sourceHigh confidence · 82%latest vmain@78f2461 Repository

Declared MCP capabilities

ToolsResourcesPrompts

Run it securely

Host leeguooooo/iphone-use in a governed environment — SSO in front, every tool call attributed and audited.

Are you the maintainer?

Verify with GitHub to get alerted whenever leeguooooo/iphone-use changes score — and claim the badge for your README.

Claim this server

The short answer

Is iphone-use safe to use?: iphone-use scores 83/100 (grade B) on the Canopii Trust Index — good, minor gaps. It passes 11 of the 21 security controls that apply to it, with no confirmed security failures.
How reliable is the security score for iphone-use?: We could evaluate 82% of the controls that apply to iphone-use. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.
How was iphone-use scored?: Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.

Reputation185stars19forks0open issues1d agolast commit<1yage

Security controlslatest scored version vmain@78f2461

Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

Pass
In-Session Definition Integrityguardno call-gated or call-time tool definition changes
Tool and prompt definitions stay fixed during a session — they don't change after a few calls, which is how runtime-gated rug-pulls slip past one-time review.
Not checked
Indirect Prompt Injection (IPI) Defensesguardno tools extracted
Tool/prompt/resource text is free of hidden instructions that could hijack the agent.
Not checked
Strict JSON Schema Enforcementno tool schemas found
Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.
Not checked
User-in-the-Loop / Approval Scopeguardno tools extracted
No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.
N/A
Tool Definition Integrityguardno prior version to diff
Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

Application Security Checks

Warn
No path traversalguard3 occurrences (build/test paths only)
Naive path checks let tools read/write outside intended directories (EscapeRoute-class).
docs/measurements/agent-loop-ab-2026-10-07/ab.py:163docs/measurements/agent-loop-ab-2026-10-07/ab.py:188docs/measurements/agent-loop-ab-2026-10-07/ab.py:198
Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.
Warn
No SSRF sinksguard6 occurrences (build/test paths only)
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
docs/measurements/agent-loop-ab-2026-10-07/ab.py:47scripts/bench-census.py:54scripts/flow-reverify.py:66scripts/runner-compat.py:50
Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.
Warn
No known-vulnerable dependencies6 of 351 runtime deps vulnerable; worst high
Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.
[email protected] — RUSTSEC-2026-0190[email protected] — GHSA-4w2j-m93h-cj5j[email protected] — RUSTSEC-2026-0185[email protected] — GHSA-33f5-2c5q-wgwj
Fix: Upgrade the flagged dependencies past their fixed versions.
Warn
Declares a licenseno recognized license
A clear license is required for legal enterprise use.
Fix: Add a recognized SPDX license (MIT, Apache-2.0, …).
Warn
Has a security policyno security policy
A SECURITY.md gives a private path to report vulnerabilities.
Fix: Add SECURITY.md with a disclosure contact and process.
Pass
No command-injection sinksguardno sinks found
Untrusted tool input reaching a shell yields remote code execution.
Pass
No dynamic code executionguardno sinks found
eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.
Pass
No unsafe deserializationguardno sinks found
pickle/yaml.load/etc. on untrusted data can execute code.
Pass
No committed secretsguardno secrets found
Hardcoded keys/tokens in published source are live credentials an attacker can use.
Pass
Credentials sourced from environmentreads credentials from environment
Reading secrets from env/secret stores avoids hardcoding them.
Pass
Dependencies pinned (lockfile)lockfile present
A lockfile makes installs reproducible and resistant to silent dependency swaps.
Pass
Actively maintainedrecent commits
Unmaintained servers don't receive security fixes.
Pass
Repository not archivedguardactive
Archived repositories will never be patched.
Pass
Adoption & popularityestablished adoption
A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.
Not checked
Signed releasesnot evaluated
Signed releases let consumers verify artifacts weren't tampered with.
N/A
No install/post-install scriptsguardno published package
install hooks run arbitrary code on every consumer at install time.
N/A
Package name not typosquattingguardno published package
Names mimicking popular packages are a common malware delivery vector.
N/A
Published with provenanceno published package
Build provenance attests the artifact was built from the claimed source by CI.
N/A
Established maintainerno published package
Brand-new / single anonymous maintainers raise takeover and malware risk.

Transport & Trust Model

Warn
Execution Sandboxingruns natively (no container image)
A container/sandbox image limits blast radius; a server that runs natively has full host access.
Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.
Pass
Network Exposureno bind-all detected
Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.
N/A
Transport Encryption (TLS)guardno remote endpoints
Plaintext HTTP exposes traffic and bearer tokens to interception.
N/A
IAM / Authentication Scopingno remote endpoints
OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.
N/A
No Token Passthroughguardno HTTP transport
The client's token is never forwarded to downstream APIs — the server obtains its own, correctly-scoped credential instead.
N/A
DNS-Rebinding Protectionno HTTP transport
HTTP endpoints reject requests carrying an unlisted Origin, so a malicious web page can't drive the server through the user's browser.
N/A
Live Endpoint Reachablenot dynamically scanned
A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.
N/A
Authentication Enforced (live)not dynamically scanned
If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Embed this score

Add the live badge to your README — it updates automatically on every rescan.

markdown

[![Canopii Trust Score](https://index.canopii.dev/api/badge/leeguooooo/iphone-use)](https://index.canopii.dev/server/leeguooooo/iphone-use)

html

<a href="https://index.canopii.dev/server/leeguooooo/iphone-use"><img src="https://index.canopii.dev/api/badge/leeguooooo/iphone-use" alt="Canopii Trust Score" /></a>

Versions

Version	Score	Status	Published
vmain@78f2461latest	83B	scored	10/11/2026

Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.