CanopiiCanopiiAll serversEnterprise →
sandraschi/windows-computer-use-mcp

sandraschi/windows-computer-use-mcp vmaster@6d80086

Security Trust Score
Grade F · Serious issues
Tier 1 · Public sourceHigh confidence · 98%
Declared MCP capabilities

This server scored F. Run it behind runtime policy enforcement so one bad tool call can't become an incident.

2 issues capping this score
  • criticalNo command-injection sinks — 5 occurrences
  • highNo unsafe deserialization — 3 occurrences
Reputation25stars7forks2open issues9d agolast commit1yage

Security controls

Deterministic, evidence-backed. Score earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

  • Pass
    Indirect Prompt Injection (IPI) Defensesguardno injection markers

    Tool/prompt/resource text is free of hidden instructions that could hijack the agent.

  • Pass
    Strict JSON Schema EnforcementadditionalProperties:false present

    Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.

  • Pass
    User-in-the-Loop / Approval Scopeguardno destructive tool scope

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.

  • N/A
    Tool Definition Integrityguardno prior version to diff

    Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

Application Security Checks

  • Fail
    No command-injection sinksguard5 occurrences

    Untrusted tool input reaching a shell yields remote code execution. How many servers fail this?

    scripts/demo-autonomous.py:190scripts/paint_demo.py:27scripts/text_demo.py:32scripts/text_demo.py:35

    Fix: Never pass tool arguments to a shell; use argv arrays with shell disabled.

  • Fail
    No unsafe deserializationguard3 occurrences

    pickle/yaml.load/etc. on untrusted data can execute code. How many servers fail this?

    src/windows_computer_use_mcp/face_recognition.py:74src/windows_computer_use_mcp/tools/archived/face_recognition.py:129src/windows_computer_use_mcp/tools/portmanteau_face.py:118

    Fix: Use safe loaders (yaml.safe_load, JSON) on untrusted input.

  • Warn
    No path traversalguard3 occurrences

    Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

    web_sota/src/components/layout/topbar.tsx:34web_sota/src/hooks/useMcpSetup.ts:69web_sota/src/lib/api.ts:10

    Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

  • Warn
    No SSRF sinksguard29 occurrences

    Fetching tool-supplied URLs can pivot into internal networks and metadata services.

    scripts/cua-smoke.py:162scripts/cua-smoke.py:388scripts/cua-smoke.py:435scripts/cua-smoke.py:449

    Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.

  • Warn
    No known-vulnerable dependencies36 of 827 runtime deps vulnerable; worst high

    Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.

    [email protected] — RUSTSEC-2026-0190[email protected] — RUSTSEC-2024-0413[email protected] — RUSTSEC-2024-0416[email protected] — RUSTSEC-2024-0412

    Fix: Upgrade the flagged dependencies past their fixed versions.

  • Pass
    No dynamic code executionguardno sinks found

    eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.

  • Pass
    No committed secretsguardno secrets found

    Hardcoded keys/tokens in published source are live credentials an attacker can use.

  • Pass
    Credentials sourced from environmentreads credentials from environment

    Reading secrets from env/secret stores avoids hardcoding them.

  • Pass
    Dependencies pinned (lockfile)lockfile present

    A lockfile makes installs reproducible and resistant to silent dependency swaps.

  • Pass
    Actively maintainedrecent commits

    Unmaintained servers don't receive security fixes.

  • Pass
    Repository not archivedguardactive

    Archived repositories will never be patched.

  • Pass
    Declares a licenseMIT

    A clear license is required for legal enterprise use.

  • Pass
    Has a security policySECURITY.md present

    A SECURITY.md gives a private path to report vulnerabilities.

  • Pass
    Adoption & popularityestablished adoption

    A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.

  • Not checked
    Signed releasesnot evaluated

    Signed releases let consumers verify artifacts weren't tampered with.

  • N/A
    No install/post-install scriptsguardno published package

    install hooks run arbitrary code on every consumer at install time.

  • N/A
    Package name not typosquattingguardno published package

    Names mimicking popular packages are a common malware delivery vector.

  • N/A
    Published with provenanceno published package

    Build provenance attests the artifact was built from the claimed source by CI.

  • N/A
    Established maintainerno published package

    Brand-new / single anonymous maintainers raise takeover and malware risk.

Transport & Trust Model

  • Warn
    Execution Sandboxingruns natively (no container image)

    A container/sandbox image limits blast radius; a server that runs natively has full host access.

    Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.

  • Warn
    Network Exposurebinds 0.0.0.0

    Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.

    Fix: Bind to 127.0.0.1 by default; never ship open debug endpoints.

  • N/A
    Transport Encryption (TLS)guardno remote endpoints

    Plaintext HTTP exposes traffic and bearer tokens to interception.

  • N/A
    IAM / Authentication Scopingno remote endpoints

    OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.

  • N/A
    Live Endpoint Reachablenot dynamically scanned

    A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.

  • N/A
    Authentication Enforced (live)not dynamically scanned

    If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Tools (80)

waithellomy_tooladd_faceget_helpcalculatepress_keysend_keystool_functool_nametype_textasync_taskmove_mousewrite_notedelete_facehello_worldhover_mousesync_statustest_configtest_importverify_textexample_toolforce_rescangreet_personhealth_checklist_deviceslist_windowspress_hotkeyscroll_mousetest_importsclick_elementhover_elementsystem_healthelement_existsrecognize_faceasync_operationclose_firefox_dbget_all_elementsget_element_infoget_element_rectget_element_textlist_known_facesmanage_bookmarkssearch_bookmarksset_element_textwait_for_elementautomation_safetyclick_at_positionfetch_device_listget_desktop_stateget_device_statusparse_device_datasync_health_checkapprove_automationfix_invisible_textget_bookmark_by_idis_element_enabledis_element_visibleget_cursor_positionget_security_eventsright_click_elementstop_app_monitoringdouble_click_elementfind_window_by_titleget_system_clipboardset_system_clipboardstart_app_monitoringauthenticate_nest_apicapture_and_recognizeconnect_to_firefox_dbcount_total_bookmarksget_bookmark_overviewlist_bookmark_folderssearch_bookmarks_by_urlstop_intruder_detectionstart_intruder_detectionget_app_monitoring_statusget_bookmark_table_schemasearch_bookmarks_by_titleget_intruder_detection_status