Sato Renga

Building AI dev tools

About

PMO in the IT industry, building OSS and small products with AI-driven development. Interested in making AI tools safer, more useful, and more accessible to people without a traditional coding background.

Badges

Tastemaker

Gone streaking

Gone streaking 5

Maker History

AgentRiskScan untrusted AI-agent repos before your agent runs them
Jul 2026

🎉

Joined Product HuntApril 3rd, 2026

Forums

•

3d ago

AgentRisk - Scan untrusted AI-agent repos before your agent runs them

AgentRisk is a zero-execution preflight scanner and local MCP server for AI-agent artifacts. Point it at a folder, GitHub URL, npm package, or tarball before your coding agent opens it. It flags risky MCP launchers, install scripts, secret-forwarding config, and repo instructions like "read .env" or "ignore approval". Use it from the CLI or as an MCP tool: npx --yes agentrisk@latest mcp config. Exports JSON, Markdown, SARIF, and terminal reports.