Lock Down the Machine: Workstation Security for Claude Codeadvanced · ~110 min

Attack Your Own Agent — Build a Prompt-Injection Red-Team Harness for Claude Code

Your permission rules and egress gates were built against an imagined attacker. How do you find out — safely, on your own machine — whether they actually stop an instruction hidden in a file, a script's output, or a page your agent reads during ordinary work?

🤝 Want this built for you? Start a request — our AI scopes it, estimates a price range, and matches you with a vetted AI Advisor. →

Two ways to open it

Just this build

$40 one-time

Unlocks this full walkthrough on your account — no subscription, and no account needed until you check out. Advisor-grade build.

Best value Rovvi AI Advisor membership

$69 / month

Every Ambassador-exclusive build, first access to new ones, and your spot on the advisor-only needs board. Or $300/year.

Become an Advisor to unlock →

What you'll do

A reusable, fully manifested red-team harness that plants four inert canary payloads in four content channels, runs real Claude Code sessions against them, and produces a signed verdict table showing which boundary blocked which attempt, which attempt landed, and whether your audit ledger recorded it.