Whiskor MCP Server
whiskor
npm
v0.16.2
Source verified
Published by torotorotrpg — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 14
high Dynamic code execution in server code (extension/injected/executor.js)MTC-SRC-001
In the server's implementation (`extension/injected/executor.js:1565`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const result = new Function(`return (${action.code})`)(); if (result instanceof Promise) { re
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server extension/injected/executor.js
high Dynamic code execution in server code (firefox-mv2/injected/executor.js)MTC-SRC-001
In the server's implementation (`firefox-mv2/injected/executor.js:1565`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const result = new Function(`return (${action.code})`)(); if (result instanceof Promise) { re
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server firefox-mv2/injected/executor.js
high Dynamic code execution in server code (shared/injected/executor.js)MTC-SRC-001
In the server's implementation (`shared/injected/executor.js:1565`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const result = new Function(`return (${action.code})`)(); if (result instanceof Promise) { re
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server shared/injected/executor.js
high Shell/command execution in server code (server/cli-shell.js)MTC-SRC-002
In the server's implementation (`server/cli-shell.js:241`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const shells = pickShells(); for (let i = 0; i < shells.length; i++) {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server server/cli-shell.js
high Shell/command execution in server code (server/cli.js)MTC-SRC-002
In the server's implementation (`server/cli.js:825`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const child = spawn(process.execPath, [supervisorPath, ...serverFlags], {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server server/cli.js
high Shell/command execution in server code (server/services/ocr-service.js)MTC-SRC-002
In the server's implementation (`server/services/ocr-service.js:25`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require('child_process'); let _config = {}; let _resolved = false; let _engine = null; // { binPath, ver
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server server/services/ocr-service.js
high Shell/command execution in server code (server/update-checker.js)MTC-SRC-002
In the server's implementation (`server/update-checker.js:20`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const path = require('path'); // The bundled cross-platform notifier (scripts/
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server server/update-checker.js
medium Dynamic module load from a non-literal (extension/injected/executor.js)MTC-SRC-005
In the server's implementation (`extension/injected/executor.js:1751`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: mod = await withTimeout(import(url), timeoutMs); const evaluatedMs = Date.now() - injectedAt; let value
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server extension/injected/executor.js
medium Dynamic module load from a non-literal (firefox-mv2/injected/executor.js)MTC-SRC-005
In the server's implementation (`firefox-mv2/injected/executor.js:1751`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: mod = await withTimeout(import(url), timeoutMs); const evaluatedMs = Date.now() - injectedAt; let value
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server firefox-mv2/injected/executor.js
medium Dynamic module load from a non-literal (shared/injected/executor.js)MTC-SRC-005
In the server's implementation (`shared/injected/executor.js:1751`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: mod = await withTimeout(import(url), timeoutMs); const evaluatedMs = Date.now() - injectedAt; let value
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server shared/injected/executor.js
low Shell/command execution in packaging/dev tooling (scripts/_check-config-defaults.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/_check-config-defaults.js:28`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: d: false, why: 'dev-exec (live arbitrary code execution) must be opt-in — enable it in config.local.json' }, { pat
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/_check-config-defaults.js
low Shell/command execution in packaging/dev tooling (scripts/_notify.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/_notify.js:22`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require('child_process'); const title = process.argv[2] || 'whiskor'; const message = process.argv[3] ||
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/_notify.js
low Shell/command execution in packaging/dev tooling (scripts/_run-tests.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/_run-tests.js:14`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require('child_process'); const fs = require('fs'); const os = require('os'); const path = require('path'
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/_run-tests.js
low Shell/command execution in packaging/dev tooling (scripts/supervisor.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/supervisor.js:33`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const path = require('path'); const WORKER = path.join(__dirname, '..', 'serve
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/supervisor.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.16.2 latest |
A 94/100 | 14 | 1.9.0 | 2026-07-24 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan whiskor --onlineMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.