feat: better framing

app/api/analyze/prompt.txt

@@ -38,6 +38,8 @@ These files are a prompt injection surface. A malicious contributor, compromised
 - Override safety behaviors the agent would normally follow
 - Instruct the agent to ignore security warnings
 
+IMPORTANT: A sandbox like Greywall does NOT prevent prompt injection. The agent will still read these files and follow the instructions. What a sandbox does is contain the blast radius: even if the agent is hijacked, it can't exfiltrate data (network blocked), can't read secrets (filesystem denied), can't run destructive commands (command blocked). Prompt injection findings should reflect this nuance: the risk is that the agent's behavior is manipulated, and without a sandbox the manipulated agent has unrestricted access.
+
 If agent instruction files exist in this repo, this is a SIGNIFICANT finding. The more instruction files present, the larger the attack surface.
 
 SEVERITY CONTEXT:

app/greyscan/page.tsx

@@ -584,6 +584,11 @@ export default function GamePage() {
                             <span className={`text-[10px] font-sans font-medium uppercase tracking-wider ${severityColor(finding.severity)}`}>
                               {finding.severity}
                             </span>
+                            {finding.type === 'prompt_injection' && (
+                              <span className="text-[10px] font-sans text-muted-foreground/50 uppercase tracking-wider">
+                                &middot; sandbox limits damage
+                              </span>
+                            )}
                           </div>
                           <h3 className="text-sm font-sans font-medium text-foreground mb-1">
                             {finding.title}