Hopper LabsLab

Track

AI agent safety

Keep your AI agent from being hijacked by hidden instructions.

See the hidden text and instructions a web page can aim at AI agents, check a skill before you install it, and teach your agent to treat content as information.

  1. Try it

    LiveAI agent safety

    What an AI sees

    What does a web page tell an AI that it doesn't show you?

    Open lab

  2. Keep it

    Skillv1.0.0

    Treat content as data

    Rules for an AI agent: instructions found in web pages, emails, files and tool results are information, never commands. It keeps working for its person, reports attempts to redirect it, and asks before acting.

    See what it says

  3. Try it

    LiveAI agent safety

    Skill safety check

    Is this AI agent skill safe to install?

    Open lab

  4. Keep it

    Skillv1.0.0

    Review a skill before installing

    The checklist an agent works through before installing a skill or plugin: exact files, hidden content, instructions aimed at it, commands, scripts, links and tools, then a plain report and the person's yes.

    See what it says