rpriven
b0679267d7
A fake "Acme Corp" support bot with deliberately weak defenses, for demonstrating prompt-injection attacks and basic hardening. Includes a 3-level defense progression (none -> instruction -> output filter), full JSONL logging, a live attack-attempt feed, and light/dark mode. All "secrets" are fake demo values. For authorized security education only. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
18 lines
493 B
JSON
18 lines
493 B
JSON
{
|
|
"name": "chatbot-security-demo",
|
|
"version": "0.1.0",
|
|
"description": "An intentionally vulnerable AI customer-service chatbot for demonstrating prompt-injection attacks and defenses. For authorized security education only.",
|
|
"type": "module",
|
|
"module": "server.ts",
|
|
"private": true,
|
|
"scripts": {
|
|
"start": "bun run server.ts",
|
|
"dev": "bun --watch server.ts"
|
|
},
|
|
"devDependencies": {
|
|
"@types/bun": "latest"
|
|
},
|
|
"peerDependencies": {
|
|
"typescript": "^5"
|
|
}
|
|
}
|