CanopiiCanopiiAll serversEnterprise →

clawdcursor MCP Server Security Report

AmrDab/clawdcursor

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

Security Trust Score
Grade F · Serious issues
Tier 1 · Public sourceHigh confidence · 98%latest vmain@37a06fc Repository
Declared MCP capabilities
ResourcesPrompts

Run it securely

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

Are you the maintainer?

Verify with GitHub to get alerted whenever AmrDab/clawdcursor changes score — and claim the badge for your README.

Claim this server
2 issues capping this score
  • criticalNo command-injection sinks — 5 occurrences
  • mediumNo over-broad / destructive tools — 1 over-broad tool(s)

The short answer

Is clawdcursor safe to use?
clawdcursor scores 14/100 (grade F) on the Canopii Trust Index, and carries 2 confirmed security failures that cap its score: No command-injection sinks and No over-broad / destructive tools. It passes 14 of the 24 controls that apply to it.
What security issues does clawdcursor have?
clawdcursor fails 2 controls: No command-injection sinks and No over-broad / destructive tools. Each failure on this page carries the evidence behind it — the file and line, dependency, or CVE that decided it.
How reliable is the security score for clawdcursor?
We could evaluate 98% of the controls that apply to clawdcursor. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.
Does clawdcursor have any security advisories?
clawdcursor has 4 non-scoring advisories — observations worth a human review that deliberately do not affect the deterministic score, since they can be noisy.
How was clawdcursor scored?
Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.
Reputation406stars59forks19open issuestodaylast commit<1yage

Security controlslatest scored version vmain@37a06fc

Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

  • Fail
    User-in-the-Loop / Approval Scopeguard1 over-broad tool(s)

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval. How many servers fail this?

    system

    Fix: Scope tools narrowly; avoid arbitrary command execution and destructive defaults.

  • Warn
    Tool Definition Integrityguard4 tool description(s) drifted after publish (no risk signals in 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.

    read_screenverifyclicksubmit_task

    Fix: Never add hidden directives or destructive scope to an already-published tool; document description changes in release notes.

  • 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
    In-Session Definition Integrityguardno call-gated or call-time tool definition changes

    Tool and prompt definitions stay fixed during a session — they don't change after a few calls, which is how runtime-gated rug-pulls slip past one-time review.

Application Security Checks

  • Fail
    No command-injection sinksguard5 occurrences

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

    src/surface/cli.ts:146src/surface/cli.ts:161src/surface/cli.ts:168src/surface/cli.ts:185

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

  • Warn
    No dynamic code executionguard1 occurrence (build/test paths only)

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

    src/__tests__/dashboard-surface.test.ts:62

    Fix: Remove eval/exec; parse and dispatch explicitly.

  • Warn
    No path traversalguard62 occurrences

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

    scripts/bundle-cli.mjs:53src/__tests__/agent-browser-profile.test.ts:21src/__tests__/agent-tools-characterization.test.ts:524src/__tests__/linux-adapter.test.ts:81

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

  • Warn
    No SSRF sinksguard63 occurrences

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

    scripts/verify-macos.mjs:300src/__tests__/mcp-http-transport.test.ts:67src/__tests__/mcp-http-transport.test.ts:88src/__tests__/mcp-http-transport.test.ts:145

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

  • Warn
    No known-vulnerable dependencies1 of 255 runtime deps vulnerable; worst medium

    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] — GHSA-5v7r-6r5c-r473

    Fix: Upgrade the flagged dependencies past their fixed versions.

  • Pass
    No unsafe deserializationguardno sinks found

    pickle/yaml.load/etc. on untrusted data can execute code.

  • 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.

  • Pass
    No Token Passthroughguardno inbound token forwarded downstream

    The client's token is never forwarded to downstream APIs — the server obtains its own, correctly-scoped credential instead.

  • Pass
    DNS-Rebinding ProtectionOrigin header checked and rejected with 403

    HTTP endpoints reject requests carrying an unlisted Origin, so a malicious web page can't drive the server through the user's browser.

  • 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.

AI-flagged — for review

Observations from an AI review of tool descriptions. These are advisory only and do not affect the score — they can be noisy and need human judgement.

  • info
    Tool "verify" description changed after publish

    Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.

  • info
    Tool "click" description changed after publish

    Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.

  • info
    Tool "submit_task" description changed after publish

    Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.

Show 1 more

Embed this score

Add the live badge to your README — it updates automatically on every rescan.

Canopii Trust Score badge preview
markdown[![Canopii Trust Score](https://index.canopii.dev/api/badge/AmrDab/clawdcursor)](https://index.canopii.dev/server/AmrDab/clawdcursor)
html<a href="https://index.canopii.dev/server/AmrDab/clawdcursor"><img src="https://index.canopii.dev/api/badge/AmrDab/clawdcursor" alt="Canopii Trust Score" /></a>

Versions

VersionScoreStatus
vmain@37a06fclatest14Fscored
vmain@9a90cee14Fscored
vmain@d50a28b14Fscored
vmain@fb32ce014Fscored
vmain@b961f1914Fscored
vmain@088689e14Fscored
vmain@d9c396714Fscored
vmain@c1c2f3614Fscored
vmain@99e8b3a13Fscored
vmain@2a5f9be14Fscored
vmain@a549e9a14Fscored
vmain@00592f814Fscored
vmain@83c4d3214Fscored
vmain@f302e7313Fscored
vmain@4bd85c914Fscored
vmain@d7a197613Fscored
vmain@002109b14Fscored
vmain@d1f34c313Fscored
vmain@35800c615Fscored
vmain@9fca03f15Fscored
vmain@47440c415Fscored
vmain@295e95c15Fscored
vmain@eca317b15Fscored
vmain@272fa4015Fscored
vmain@89c769915Fscored
vmain@bd817bc15Fscored
vmain@c2f1f8716Fscored
vmain@b95c80b16Fscored
vmain@c56683116Fscored
vmain@44eb34216Fscored
vmain@7d3464216Fscored
vmain@fcaae7d16Fscored
vmain@e5f545616Fscored
vmain@f838f0216Fscored
vmain@742fe9716Fscored
vmain@cda0c0b16Fscored
vmain@c5ab40216Fscored
vmain@fc37deb16Fscored
vmain@4466e2716Fscored
vmain@64aede616Fscored
vmain@0da7a9a16Fscored
vmain@a49f9ce16Fscored
vmain@027595216Fscored
vmain@fd8577a16Fscored
vmain@0d1b86216Fscored
vmain@cd8dafb16Fscored
vmain@ba4f4cb16Fscored
vmain@5cab29616Fscored
vmain@f091d9a16Fscored
vmain@9f788db16Fscored
vmain@776118316Fscored
vmain@5c229a816Fscored
vmain@d03881116Fscored
vmain@3d99eab16Fscored
vmain@542db5516Fscored
vmain@05c4d0516Fscored
vmain@20ec1d115Fscored
vmain@c738bc316Fscored
vmain@40ff18016Fscored
vmain@cfede5016Fscored
vmain@76ac95d16Fscored
vmain@56fcb3e16Fscored
vmain@4b8df1916Fscored
vmain@73027f716Fscored
vmain@5b27bd716Fscored
vmain@1eb0d3616Fscored
vmain@f74373316Fscored
vmain@ff6376916Fscored
vmain@d00b14816Fscored
vmain@ce17a9816Fscored
vmain@36c90a116Fscored
vmain@4f0b87f16Fscored
vmain@245d01716Fscored
vmain@84ceaf216Fscored
vmain@02e000e16Fscored
vmain@2f270c516Fscored
vmain@6c8ed6a16Fscored
vmain@50b7ba116Fscored
vmain@990f94516Fscored

Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.