Verdict runs on your own machine — the client starts it, so there is no endpoint to ping.
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
Nothing serious here today
Today is the operative word: we check Verdict every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Alternatives to Verdict
same job, measured the same wayAsk if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
Attestari's verdict on an npm or PyPI package version, asked before an agent installs it.
Your agent asks before it acts, so the same real-world action is attempted at most once.
Tells your agent if a link is safe before it clicks, signs in or pays.
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
Risk score for a Base wallet before your agent pays it: 0-100, verdict and explained flags.
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
Verdict — questions
Answers built from our own checks of this server.