Skills/PyPI/torbrowser-mcp

torbrowser-mcp@0.1.0

VERIFIED· not started

Publisher claims: "MCP server for stock Tor Browser automation via geckodriver and Marionette" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher boti-ormandi · publishing for 186 daysInstalls 101Last detonated 1 h ago
$claude mcp add torbrowser-mcp -- uvx torbrowser-mcp
WatchReport an issue

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: Verified 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso torproject.org — 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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx torbrowser-mcp

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 2026-11-20 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtests/test_process_guardian.py:33 · Python subprocess execution detectedproc = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(60)"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_lifecycle_smoke_integration.py:182 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_process_guardian.py:60 · Python subprocess execution detected"child = subprocess.Popen([sys.executable, '-c', 'import time; time.sleep(120)'])\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_process_guardian.py:66 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_lifecycle_smoke_integration.py:208 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_proxy_intercept_socks_adapter.py:94 · 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 commandtests/test_process_guardian.py:31 · Process kill command — agent can terminate processes# os.getpid() would kill the test runner at interpreter shutdown.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtorbrowser_driver/tor_process.py:343 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtorbrowser_driver/tor_process.py:228 · Process kill command — agent can terminate processeselse "kill the stale tor process"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtorbrowser_driver/_process_guardian.py:11 · Process kill command — agent can terminate processesexit and ``Ctrl-C``. A truly hard kill of the Python parent (``SIGKILL``,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtorbrowser_mcp/tool_module.py:72 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtorbrowser_mcp/tool_module.py:74 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtorbrowser_driver/browser_process.py:135 · Process kill command — agent can terminate processesupdate kill switch, the load strategy, and the TB-specific promptFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_core_primitives.py:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdrv.browser_navigate("file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_core_primitives.py:381 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdrv.browser_tabs("new", url="file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python exec or eval of computed codetorbrowser_driver/_unsafe_primitives.py:123 · Python exec or eval of computed codeexec(source, globals_dict)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandtests/test_lifecycle_smoke_integration.py:145 · Process kill command — agent can terminate processes"""Force-kill the parent Python; bundled tor and geckodriver must die too."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈56 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 torbrowser-mcp@0.1.0 as of 38 min ago. This is the package itself, not its dependencies.

torbrowser-mcp@0.1.0 safety verdict: Verified (not started) — KillerSkills