Skills/PyPI/agentic-windows-mcp

agentic-windows-mcp@0.9.10

VERIFIED· not started

Publisher claims: "Agentic Windows MCP - an MCP server that gives AI agents full, safe control of a Windows PC: desktop automation, remote computer control, browser DevTools inspection, and remote software development." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher homenewstar · publishing for 28 daysInstalls 2,609Last detonated 15 min ago
$claude mcp add agentic-windows-mcp -- uvx agentic-windows-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 microsoft.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 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 agentic-windows-mcp

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

What changed since 0.9.9

vet-skills diff agentic-windows-mcp 0.9.9 0.9.10

In the sandbox, this version reached for nothing 0.9.9 did not. Compared from the two recorded runs, not from source.

0.9.9 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-22 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 · 1 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 detectedsrc/agentic_windows_mcp/__main__.py:1005 · Python subprocess execution detectedmkcert = subprocess.run(["where", "mkcert"], capture_output=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agentic_windows_mcp/__main__.py:1014 · 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/agentic_windows_mcp/__main__.py:1009 · Python subprocess execution detectedinstall = subprocess.run(["mkcert", "-install"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agentic_windows_mcp/powershell/jobs.py:280 · 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
Process kill commandsrc/agentic_windows_mcp/process/service.py:88 · Process kill command — agent can terminate processesreturn "Error: Provide either pid or name parameter for kill mode."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/agentic_windows_mcp/__main__.py:1242 · Python subprocess execution detectedreturn subprocess.run(["schtasks", *args], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agentic_windows_mcp/powershell/utils.py:223 · Python subprocess execution detectedwith subprocess.Popen(*popenargs, **kwargs) as process:Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.md:270 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. Settings → Connectors → enable Developer mode → *Create* a new connector.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:268 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileChatGPT supports MCP through **Developer mode / Connectors**:Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandsrc/agentic_windows_mcp/tools/process.py:14 · Process kill command — agent can terminate processes…nalytics): @mcp.tool( name="Process", description='List and kill running processes. Keywords: task manager, running tasks, kill, terminate, stop …Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/agentic_windows_mcp/powershell/utils.py:272 · 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 detectedsrc/agentic_windows_mcp/tools/app.py:50 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agentic_windows_mcp/__main__.py:1032 · 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/agentic_windows_mcp/__main__.py:1269 · Python subprocess execution detectedreturn 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/agentic_windows_mcp/powershell/jobs.py:358 · 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 detectedsrc/agentic_windows_mcp/powershell/utils.py:250 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/agentic_windows_mcp/process/service.py:110 · Process kill command — agent can terminate processesreturn f"Access denied to kill PID {pid}. Try running as administrator."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/agentic_windows_mcp/tools/process.py:1 · Process kill command — agent can terminate processes"""Process tool — list and kill running processes."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageREADME.md:270 · Authorization escalation language · informational: not an instruction file1. Settings → Connectors → enable Developer mode → *Create* a new connector.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Context shift attemptREADME.md:270 · Context shift attempt — trying to change operational mode · informational: not an instruction file1. Settings → Connectors → enable Developer mode → *Create* a new connector.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/agentic_windows_mcp/powershell/utils.py:271 · Process kill command — agent can terminate processeslogger.debug('Other exception occurred, attempting to kill process...')Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.md:318 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| ChatGPT | HTTP connector (Developer mode) | Developer mode must be enabled |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:268 · Authorization escalation language · informational: not an instruction fileChatGPT supports MCP through **Developer mode / Connectors**:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:318 · Authorization escalation language · informational: not an instruction file| ChatGPT | HTTP connector (Developer mode) | Developer mode must be enabled |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈90 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

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