Skills/PyPI/mcp-phone-controll

mcp-phone-controll@0.21.0

CAUTION· not started

Publisher claims: "MCP server for building, deploying and testing Flutter apps on real Android + iOS devices" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher michal-giza · publishing for 179 daysInstalls 164Last detonated 6d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
MCP_HTTP_API_KEYConfiguration, not credentials: MCP_ARTIFACTS_DIR, MCP_AUTO_NARRATE_EVERY, MCP_HTTP_HOST, MCP_HTTP_PORT, MCP_IOS_SIM_WDA_PORT, MCP_IOS_WDA_SNAPSHOT_DEPTH, MCP_LLM_BASE_URL, MCP_LLM_MODEL, MCP_LOG_FORMAT, MCP_MAX_IMAGE_DIM, MCP_PROGRESS_LOG, MCP_QUIET, MCP_REFLEXION_RETRIES, MCP_SKILL_LIBRARY_DB, MCP_STRICT_TOOLS, MCP_TOOL_TIER, MCP_TRACE_DB, MCP_UI_CACHE_TTL_MS, MCP_WDA_TEAM_ID
Where it talks to
no vendor host named in the codeAlso myapp.com, leancode.co — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names myapp.com, leancode.co as well as its own vendor. The guard injects MCP_HTTP_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx mcp-phone-controll

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-08 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: References a credential file in the home directory; Auto-update or dynamic fetch configuration; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
References a credential file in the home directorysrc/mcp_phone_controll/domain/path_guard.py:5 · References a credential file in the home directory`~/.ssh/id_rsa.png` and clobber it. We added a per-tool guard there.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_phone_controll/domain/usecases/plan.py:19 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"HOT_RELOAD": ("DEV_SESSION_START",),Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_phone_controll/domain/usecases/recall.py:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"**/.env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_phone_controll/domain/path_guard.py:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`~/.ssh/id_rsa.png` and clobber it. We added a per-tool guard there.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandpyproject.toml:133 · Privileged sudo command — agent may execute with elevated privileges# system-wide binary (sudo doesn't see the venv PATH). InstallFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/mcp_phone_controll/domain/path_guard.py:143 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesWhat this blocks: `/etc/...`, `/root/...`, `~/.ssh/...`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedsrc/mcp_phone_controll/infrastructure/dart_cli.py:1 · Destructive file system command detected"""Async wrapper around the `dart` CLI for analyze / format / fix / pub.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/mcp_phone_controll/domain/usecases/productivity.py:496 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# `grep_logs(path="~/.ssh/known_hosts", pattern=".*")` would leakFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_phone_controll/domain/entities.py:243 · Auto-update or dynamic fetch configuration — agent may load new code at runtime# OPEN_IDE | DEV_SESSION_* | HOT_RELOAD | AR_SCENE_READY | REFLECTIONFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_phone_controll/domain/path_guard.py:42 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# like `/etc/passwd`, `/root/...`, `~/.ssh/`, `/Library/...`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_phone_controll/domain/usecases/recall.py:99 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"**/.env.*",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedsrc/mcp_phone_controll/domain/usecases/code_quality.py:3 · Destructive file system command detectedThese wrap `dart analyze / format / fix` and `flutter pub get / outdated`.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_phone_controll/data/image_capping.py:206 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_phone_controll/version_info.py:53 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/mcp_phone_controll/domain/usecases/wda_setup.py:625 · Process kill command — agent can terminate processes# so we'd spawn xcodebuild, wait the full timeout, kill a runnerFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_phone_controll/domain/usecases/wda_setup.py:381 · Process kill command — agent can terminate processes# Timeout — try to kill the xcodebuild we spawned.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_phone_controll/domain/usecases/deep_link.py:141 · Process kill command — agent can terminate processes# Cold-start: kill the app first. Without the package_id weFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_phone_controll/domain/usecases/ocr.py:112 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandsrc/mcp_phone_controll/infrastructure/tunneld_probe.py:10 · Privileged sudo command — agent may execute with elevated privilegesneeds sudo and stays as a manual setup step), it just answers the questionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/mcp_phone_controll/__main__.py:12 · Process kill command — agent can terminate processes(Claude Desktop quit, Mac sleep, `kill -TERM`) orphansFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈62 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for mcp-phone-controll@0.21.0 as of 6d ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim michal-giza: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim michal-gizaPropose a patch to the maintainer