monadical/greywall-landing-page
13
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: better phrasing

Browse Source
This commit is contained in:
Nik L
2026-03-16 20:18:40 -04:00
parent adea1fec5b
commit 00cb727222
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
app/api/analyze/prompt.txt
View File

@@ -1,4 +1,6 @@
You are a security analyst who deeply understands how AI coding agents behave when given access to a repository. Your job is to generate a realistic "Agent Threat Report" — a breakdown of exactly what an AI agent would attempt if run with unrestricted permissions on this repo.
You are a security analyst who deeply understands how AI coding agents behave. Your job is to generate a realistic threat report showing what an AI agent would attempt ON THE DEVELOPER'S MACHINE when working on this repo.
Key context: AI agents run as the user's own process with full access to their machine. The repo determines what the agent is motivated to do, but the attack surface is the developer's entire system (SSH keys, cloud credentials, shell history, env vars, network access). The agent doesn't stay within the repo boundary.
AI agents (Claude Code, Cursor, Copilot, Cline, Aider, etc.) follow predictable patterns when working on a codebase:

8
app/greyscan/page.tsx
View File

@@ -358,11 +358,11 @@ export default function GamePage() {
<div className="relative max-w-2xl w-full text-center animate-fade-up">
<h1 className="font-serif text-3xl sm:text-4xl md:text-5xl font-semibold tracking-tight leading-[1.1] mb-4">
What would an AI agent{' '}
<em className="italic text-primary">try</em> on your repo?
<em className="italic text-primary">try on your machine?</em>
</h1>
<p className="text-muted-foreground font-serif text-base sm:text-lg leading-relaxed mb-10 max-w-xl mx-auto">
Paste a public GitHub URL. We&apos;ll scan your codebase and show exactly what an unrestricted AI agent would attempt.
AI agents run as you, with access to everything you have. Paste a repo URL and we&apos;ll show what an unrestricted agent would attempt on your machine when working on that codebase.
</p>
<form
@@ -475,7 +475,7 @@ export default function GamePage() {
<div className="flex items-center gap-2 mb-3">
<Shield className="h-4 w-4 text-primary" />
<span className="text-xs font-sans uppercase tracking-wider text-primary font-medium">
Agent Threat Report
What an agent would try on your machine
</span>
</div>
<h2 className="font-mono text-lg sm:text-xl text-foreground mb-1">
@@ -570,9 +570,7 @@ export default function GamePage() {
{/* CTA */}
<div className="px-6 sm:px-8 py-6 sm:py-8 border-t border-border/20 bg-card/20 text-center">
<p className="font-serif text-lg sm:text-xl font-semibold tracking-tight mb-2">
<span className="text-primary">&ldquo;</span>
This is what Greywall would have blocked.
<span className="text-primary">&rdquo;</span>
</p>
<p className="text-xs text-muted-foreground font-serif mb-5">
Container-free sandboxing with real-time observability for AI agents.