AgentSeal

Scans AI agent configs and MCP servers for supply-chain and prompt-injection risk.

Desktopfreemium

AgentSeal is an open-source security toolkit that scans AI coding agents and MCP servers for dangerous skill files, poisoned configs, and prompt-injection vulnerabilities. It supports 28+ agents including Claude Code and Cursor, runs core scans offline, and offers a free scanner plus a paid Pro tier for continuous security assessments. Built for AI security and red teams.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of AgentSeal - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim AgentSeal to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether AgentSeal (or something else) actually fits.

Try a problem