Oscribe MCP Server
oscribe
npm
v0.3.1
Published by mikealkeal — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Vision-based desktop automation engine
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 11 = 83. 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 |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 11
high Shell/command execution in server code (dist/src/cli/commands/doctor.js)MTC-SRC-002
In the server's implementation (`dist/src/cli/commands/doctor.js:6`): 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 } from 'node:child_process'; import { existsSync } from 'node:fs'; import { createRequire } from 'node:module
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 dist/src/cli/commands/doctor.js
high Shell/command execution in server code (dist/src/cli/commands/gif.js)MTC-SRC-002
In the server's implementation (`dist/src/cli/commands/gif.js:10`): 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: ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import { loadConfig } from '../../config/
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 dist/src/cli/commands/gif.js
high Shell/command execution in server code (dist/src/core/auth.js)MTC-SRC-002
In the server's implementation (`dist/src/core/auth.js:7`): 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: ort { exec } from 'node:child_process'; import { readFileSync, writeFileSync, existsSync, unlinkSync } from 'node:fs'; 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 dist/src/core/auth.js
high Shell/command execution in server code (dist/src/core/axmanual.js)MTC-SRC-002
In the server's implementation (`dist/src/core/axmanual.js:17`): 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: ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import path from 'node:path'; import { fi
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 dist/src/core/axmanual.js
high Shell/command execution in server code (dist/src/core/browser-restart.js)MTC-SRC-002
In the server's implementation (`dist/src/core/browser-restart.js:5`): 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: , execSync } from 'node:child_process'; import { appendFileSync, existsSync, mkdirSync } from 'node:fs'; import { homedi
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 dist/src/core/browser-restart.js
high Shell/command execution in server code (dist/src/core/input.js)MTC-SRC-002
In the server's implementation (`dist/src/core/input.js:6`): 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: ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import { withLogging } from './logger.js'
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 dist/src/core/input.js
high Shell/command execution in server code (dist/src/core/nvda.js)MTC-SRC-002
In the server's implementation (`dist/src/core/nvda.js:19`): 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: xec, spawn } from 'node:child_process'; import { promisify } from 'node:util'; import { existsSync, mkdirSync, writeFile
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 dist/src/core/nvda.js
high Shell/command execution in server code (dist/src/core/ocr.js)MTC-SRC-002
In the server's implementation (`dist/src/core/ocr.js:8`): 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: ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import { writeFile, unlink, mkdtemp } fro
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 dist/src/core/ocr.js
high Shell/command execution in server code (dist/src/core/screenshot.js)MTC-SRC-002
In the server's implementation (`dist/src/core/screenshot.js:5`): 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: ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import { readFile, unlink, mkdtemp, write
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 dist/src/core/screenshot.js
high Shell/command execution in server code (dist/src/core/uiautomation.js)MTC-SRC-002
In the server's implementation (`dist/src/core/uiautomation.js:8`): 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: ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import { readFileSync, existsSync, append
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 dist/src/core/uiautomation.js
medium Untrusted input concatenated into a command sink (dist/src/core/browser-restart.js)MTC-SRC-009
In the server's implementation (`dist/src/core/browser-restart.js:76`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: n32') { execSync(`rmdir /s /q "${oscribeProfile}"`, { timeout: 30000 }); } else
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 dist/src/core/browser-restart.js
Tools 24
Each tool and what it can reach — statically extracted from the published source.
os_nvda_installingests untrusted inputos_browser_restart_with_cdpno sensitive capabilityos_clickno sensitive capabilityos_click_atno sensitive capabilityos_dragno sensitive capabilityos_focusno sensitive capabilityos_hotkeyno sensitive capabilityos_inspect_atno sensitive capabilityos_mouse_downno sensitive capabilityos_mouse_upno sensitive capability
Show 14 more tools ↓
os_moveno sensitive capabilityos_nvda_startno sensitive capabilityos_nvda_statusno sensitive capabilityos_nvda_stopno sensitive capabilityos_screenshotno sensitive capabilityos_scrollno sensitive capabilityos_system_uino sensitive capabilityos_typeno sensitive capabilityos_unity_setupno sensitive capabilityos_voiceover_startno sensitive capabilityos_voiceover_statusno sensitive capabilityos_voiceover_stopno sensitive capabilityos_waitno sensitive capabilityos_windowsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (24 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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 |
|---|---|---|---|---|
v0.3.1 latest |
B 83/100 | 11 | 1.13.0 | 2026-09-07 |
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 oscribe --onlineMore in Productivity & Workflow
MCP AgentChat - 让 AI Agent 通过 Telegram 与用户实时交互：发送消息、图片，等待用户回复
A Model Context Protocol (MCP) server for Airthings Air Quality Monitor devices.
MCP server for Anki
TypeScript package for reading and searching Apple Notes on macOS via direct SQLite access. Includes markdown conversion, attachment support, and offers a local MCP server!
Verified biotech catalyst calendar (PDUFA/AdComm/trial readouts) anchored to official sources.
Appointment booking platform letting agents check provider availability and create bookings.