Skills/PyPI/winrdp-mcp

winrdp-mcp@0.1.11

CAUTION· not started

Publisher claims: "Zero-config MCP server to provision and fully administer any Windows RDP box (Win10/11/Server) — built for Claude & Claude Code." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher emog33k · publishing for 14 daysInstalls 391Last detonated 15 min ago

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
WINRDP_DEFAULT_WINRM_AUTHConfiguration, not credentials: WINRDP_AUDIT_LOG, WINRDP_CONFIRM_DESTRUCTIVE, WINRDP_DEBUG, WINRDP_HOME, WINRDP_PROFILE, WINRDP_VAULT_KEY, WINRDP_WINRM_OP_TIMEOUT
Where it talks to
no vendor host named in the codeAlso sysinternals.com, nssm.cc, python.org, chocolatey.org, aka.ms — 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 sysinternals.com, nssm.cc, python.org, chocolatey.org, aka.ms as well as its own vendor. The guard injects WINRDP_DEFAULT_WINRM_AUTH only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx winrdp-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 2026-11-21 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; README links to an external installer; Privileged sudo command. 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

MEDIUM
Python subprocess execution detectedwinrdp_mcp/transports.py:741 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandwinrdp_mcp/health.py:241 · Privileged sudo command — agent may execute with elevated privilegessr = transport.run_sh("sudo -n true && echo WINRDP_SUDO_OK", timeout=30)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
README links to an external installerREADME.md → https://example.com/tool.exehttps://example.com/tool.exeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedwinrdp_mcp/tools/rdp.py:180 · Python subprocess execution detectedsubprocess.run(["cmdkey", f"/generic:TERMSRV/{h.host}",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/transports.py:760 · 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
Privileged sudo commandtests/test_posix.py:29 · Privileged sudo command — agent may execute with elevated privileges"" if self.sudo else "sudo: a password is required", 0 if self.sudo else 1)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandwinrdp_mcp/tools/scripting.py:62 · Privileged sudo command — agent may execute with elevated privilegeshost, `elevated=True` prefixes `sudo -n`; `as_user`/`kill_on_timeout` are Windows-only.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/tools/provisioning.py:136 · Python subprocess execution detectedsubprocess.run(["cmdkey", f"/generic:TERMSRV/{h.host}", f"/user:{user}",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/tools/rdp.py:183 · Python subprocess execution detectedsubprocess.Popen(["mstsc", f"/v:{h.host}:{h.rdp_port}"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandwinrdp_mcp/tools/scripting.py:88 · Privileged sudo command — agent may execute with elevated privilegesrunner = "sudo -n " + runnerFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/transports.py:778 · Python subprocess execution detectedproc = subprocess.run(["cmd.exe", "/c", command], capture_output=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/tools/provisioning.py:127 · Python subprocess execution detectedsubprocess.run("clip", input=line.encode("utf-16-le"), check=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo commandtests/test_posix.py:27 · Privileged sudo command — agent may execute with elevated privilegesif "sudo -n true" in script:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/transports.py:780 · Python subprocess execution detectedproc = subprocess.run(shlex.split(command), capture_output=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/tools/rdp.py:158 · Python subprocess execution detectedcp = subprocess.run(["cmdkey", f"/generic:TERMSRV/{h.host}",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_sync_and_tasks.py:198 · Process kill command — agent can terminate processesThe script sleeps well past the deadline and only then writes `marker`. If the killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/tools/provisioning.py:139 · Python subprocess execution detectedsubprocess.Popen(["mstsc", f"/v:{h.host}:{h.rdp_port}"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo commandtests/test_posix.py:28 · Privileged sudo command — agent may execute with elevated privilegesreturn ExecResult("WINRDP_SUDO_OK\n" if self.sudo else "",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedwinrdp_mcp/vault.py:38 · Python subprocess execution detectedr = subprocess.run(["icacls", str(path), "/inheritance:r", "/grant:r",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandwinrdp_mcp/health.py:250 · Privileged sudo command — agent may execute with elevated privilegesf"root={uid == '0'}, sudo -n={'ok' if sudo_ok else 'unavailable'}"))Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo commandtests/test_posix.py:17 · Privileged sudo command — agent may execute with elevated privilegesself.sudo = sudoFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/tools/scripting.py:166 · Process kill command — agent can terminate processes`kill_on_timeout`: kill the remote process when `timeout` expires instead ofFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/tools/scheduling.py:144 · Process kill command — agent can terminate processes# process whose command line references that script (the task's own tree) and kill it.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/context.py:237 · Process kill command — agent can terminate processes_log.warning("kill_on_timeout: could not kill marker %s on %s: %s",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/elevation.py:243 · Process kill command — agent can terminate processesf"timeout kill it instead of leaving it running.")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/context.py:160 · Process kill command — agent can terminate processeswe meant to kill has already run to completion by the time we look for it. AFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/tools/scheduling.py:151 · Process kill command — agent can terminate processes# kill processes spawned from the task's staged script (and their children, /T)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/context.py:236 · Process kill command — agent can terminate processesexcept Exception as e: # noqa: BLE001 — the kill is best-effortFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/tools/scheduling.py:138 · Process kill command — agent can terminate processes"""Stop a running scheduled task by name and kill its process tree — the clean way toFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/context.py:181 · Process kill command — agent can terminate processestimer.join(60) # let the kill finish so the pid list is accurateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/elevation.py:258 · Process kill command — agent can terminate processes# the caller didn't ask us to kill — unregistering a task that is still runningFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/context.py:190 · Process kill command — agent can terminate processes# call, and it needs room to kill the tree before the transport gives up.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/elevation.py:131 · Process kill command — agent can terminate processes"""Stop a scheduled task AND kill the process tree it spawned; return the killed pids.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/tools/scripting.py:63 · Process kill command — agent can terminate processes`kill_on_timeout`: kill the remote python process when `timeout` expires — byFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_validate.py:35 · Destructive file system command detectedV.package("pkg; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_validate.py:35 · Destructive command against a filesystem root or deviceV.package("pkg; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandwinrdp_mcp/server.py:67 · Process kill command — agent can terminate processes# Destructive tools: delete data, kill processes, cut access, or reboot. Clients shouldFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injection attemptdocs/TOOLS.md:13 · Prompt injection attempt — model control tokens · informational: not an instruction file- [System](#system) — `winrdp_mcp/tools/system.py`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈68 tok
1 file · 74 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim emog33k: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Destructive file system command detected≈ +2 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 emog33kPropose a patch to the maintainer