Stdio Shellguard MCP Server
mcp-stdio-shellguard
npm
v0.1.2
Published by studiomeyer-io — 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.
Defense-in-depth bundle for MCP stdio servers: drop-in guard for child_process.exec/spawn, AST audit CLI for unsanitized shell calls, and a reference MCP server that exposes both. Closes the Ox-Security 200k-server stdio-RCE class.
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 − 7 = 93. 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 |
| −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 13
high Tool "guard_exec" exposes command/code executionMTC-CAP-001
Tool "guard_exec" appears to run shell commands or evaluate code (keyword "exec" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool guard_exec
high Tool "guard_spawn" exposes command/code executionMTC-CAP-001
Tool "guard_spawn" appears to run shell commands or evaluate code (keyword "spawn" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool guard_spawn
high Dynamic code execution in server code (dist/audit/patterns.js)MTC-SRC-001
In the server's implementation (`dist/audit/patterns.js:168`): 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: TICAL", label: "new Function(...)", // matches Function() calls — `new Function` parses as NewExpression
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/audit/patterns.js
high Dynamic code execution in server code (dist/audit/suggested-fix.js)MTC-SRC-001
In the server's implementation (`dist/audit/suggested-fix.js:20`): 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: ild_process: "Eliminate eval(...). If you need dynamic dispatch, use a switch over a " + "fixed table of registe
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/audit/suggested-fix.js
high Shell/command execution in server code (dist/audit/bindings.js)MTC-SRC-002
In the server's implementation (`dist/audit/bindings.js:37`): 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: ESS_SOURCES = new Set(["child_process", "node:child_process"]); /** Specifiers that denote `node:util` (for promisify 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 dist/audit/bindings.js
high Shell/command execution in server code (dist/audit/patterns.js)MTC-SRC-002
In the server's implementation (`dist/audit/patterns.js:13`): 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: _NAMES = new Set([ "child_process", "cp", "childProcess", ]); function getCalleeName(node) { const calle
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/audit/patterns.js
high Shell/command execution in server code (dist/audit/suggested-fix.js)MTC-SRC-002
In the server's implementation (`dist/audit/suggested-fix.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: ynamic_string: "Replace child_process.exec(<dynamic-string>) with " + "guard_exec({ toolName, command, args }) a
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/audit/suggested-fix.js
high Shell/command execution in server code (dist/cli.js)MTC-SRC-002
In the server's implementation (`dist/cli.js:55`): 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: sources for unsanitised child_process " + "calls. Closes the Ox-Security MCP stdio-RCE class.") .version
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/cli.js
high Shell/command execution in server code (dist/guard/exec.js)MTC-SRC-002
In the server's implementation (`dist/guard/exec.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: rt { spawn } from "node:child_process"; import { performance } from "node:perf_hooks"; import { canonicalHash } from "./
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/guard/exec.js
high Shell/command execution in server code (dist/guard/spawn.js)MTC-SRC-002
In the server's implementation (`dist/guard/spawn.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: rt { spawn } from "node:child_process"; import { performance } from "node:perf_hooks"; import { canonicalHash } from "./
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/guard/spawn.js
high Shell/command execution in server code (dist/server.js)MTC-SRC-002
In the server's implementation (`dist/server.js:111`): 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: efended replacement for child_process.exec. Forces an args[] vector, " + "runs through allowlist + sandbox +
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/server.js
low Mutating tool "guard_exec" declares no destructiveHintMTC-CAP-005
Tool "guard_exec" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool guard_exec
low Mutating tool "guard_spawn" declares no destructiveHintMTC-CAP-005
Tool "guard_spawn" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool guard_spawn
Tools 8
Each tool and what it can reach — statically extracted from the published source.
guard_execruns code / shellguard_spawnruns code / shellaudit_reportno sensitive capabilityaudit_sourceno sensitive capabilityregister_allowlistno sensitive capabilityreplay_checkno sensitive capabilitysandbox_statusno sensitive capabilitytrust_tierno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (8 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 |
|---|---|---|---|---|
v0.1.2 latest |
A 93/100 | 13 | 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 mcp-stdio-shellguard --onlineMore in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.