mobster-cli@0.4.3
CAUTION· not startedPublisher claims: "MCP server and CLI that lets Claude Code, Cursor and Codex drive a real iPhone or iOS simulator: read the screen, tap, type, and get pass/fail verdicts from accessibility assertions" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
TEXT_MODEL_API_KEYConfiguration, not credentials: COLORFGBG, COLUMNS, GOOGLE_CLOUD_PROJECT, MOBSTER_ACCOUNT_API, MOBSTER_DATA_DIR, MOBSTER_DEV_SHELL, MOBSTER_ENABLE_LIVE, MOBSTER_ENV_FILE, MOBSTER_EXPERIMENTAL_INTENTS, MOBSTER_HEDGE, MOBSTER_HEDGE_RATIO, MOBSTER_MAX_SIMS, MOBSTER_PLAIN, MOBSTER_SMART_MODEL, MOBSTER_SMART_PROVIDER, MOBSTER_THEME, MOBSTER_WDA_DEVICES, MOBSTER_WDA_URL, STY, TEXT_MODEL, TEXT_MODEL_BASE_URL, TEXT_MODEL_PROVIDER, TMUX- Where it talks to
- no vendor host named in the codeAlso claude.com, mobster.dev, tauri.localhost, openrouter.ai, google.com, groq.com, cerebras.ai, x.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 claude.com, mobster.dev, tauri.localhost, openrouter.ai, google.com, groq.com, cerebras.ai, x.com as well as its own vendor. The guard injects TEXT_MODEL_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-21 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Prompting user to enter sensitive credentials; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
handle, temporary = tempfile.mkstemp(dir=path.parent, prefix=".env-")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run(["xcrun", "swiftc", "-O", str(root / "swift" / "ocr.swift"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.completed = subprocess.run(command, capture_output=True, text=text, timeout=timeout, input=input)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen(command, stdout=stream, stderr=subprocess.STDOUT,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self._process = process or subprocess.Popen([str(part) for part in command], stdin=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.raise ValueError("Paste the API key for " + PRESETS[provider]["label"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."problem. It never runs sudo and never downloads a runtime.")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.BRAND_TEXT = re.compile("^[\u0000-\u00ff\u0131\u0152\u0153\u02bb\u02bc\u02c6\u02da\u02dc\u0304\u0308\u0329"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.process = subprocess.Popen(self.command(), cwd=self.cwd, env=self.environment(), stdout=log,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run([str(helper), str(source), str(target)], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.ps_output = subprocess.run(["ps", "-axo", "pid=,command="], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.except Exception: # noqa: BLE001 -- closing is best effort; kill belowFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."\u2000-\u206f\u20ac\u2122\u2191\u2193\u2212\u2215\u2318]*$")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.done = subprocess.run(["/bin/ps", "-p", str(int(pid)), "-o", "command="], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.with subprocess.Popen(command, stdin=subprocess.PIPE, stdout=subprocess.DEVNULL,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run([gcloud_path(), 'auth', 'print-access-token', '--quiet'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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 mobster-cli@0.4.3 as of 0 min ago. This is the package itself, not its dependencies.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim radishsoftware: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.