{"slug": "jackpot-lab-10-broken-llm-apps-you-can-poke-at-in-your-browser", "title": "Jackpot Lab: 10 Broken LLM Apps You Can Poke at in Your Browser", "summary": "A new browser-based lab at hego.red/jackpot offers ten deliberately broken LLM applications for hands-on security testing, running entirely client-side with no login or setup. The lab includes demos of prompt injection, insecure deserialization, and overly permissive tool use, and links to a GitHub repository with writeups for each vulnerability.", "body_md": "# Jackpot Lab: 10 Broken LLM Apps You Can Poke at in Your Browser\n\nI spent an afternoon wandering through [hego.red/jackpot](https://hego.red/jackpot) and it's the kind of thing that makes you grin like a kid with a chemistry set. No login, no setup — just ten tiny apps that happily do exactly the wrong thing.\n\nThe whole thing runs client-side in your browser, which itself is kind of brilliant. You're not hitting some server that logs your prompts or rate-limits you. You just open dev tools, swap a token, flip a config flag, or feed the model a slightly tweaked prompt and watch it bend.\n\nA few that stuck with me:\n\n**Prompt Injection playground**— a fake chatbot that reads a \"secret\" instruction file and cheerfully ignores it if you phrase your input just right. It's like watching a bouncer get distracted by a distraction.**Insecure Deserialization demo**— an app that takes user JSON and shoves it straight into an eval-like flow. Spoiler: it doesn't end well for the app.** Overly permissive tool use**— a mini agent that'll call tools based on whatever you type, including ones it probably shouldn't. Watching it try to \"help\" by escalating its own permissions is both funny and unsettling.\n\nWhat I like is that it's not lectureware. There's no preachy banner telling you \"this is bad.\" You just poke and the app breaks. The learning is incidental — which is exactly how it should be for this crowd.\n\nThe source links lead to a GitHub repo with writeups for each app, so you can go read about the intended vuln after you've already found three other ways to break it. That's the real charm: it invites you to fail, then explains why you failed.\n\nIf you're into prompt engineering as a hobby, or you're building LLM workflows and want a gut check on what \"bad\" looks like, this is a solid hour of messing around. I walked away with a better feel for how easily these things collapse when the guardrails are just suggestions.\n\nThe link: [hego.red/jackpot](https://hego.red/jackpot)\n\nNo sign-ups, no warnings, no hand-holding. Just ten apps waiting to be embarrassed.\n\n[Next OWASP Agentic Supply Chain: Part 5 Deep Dive →](/en/threads/4581/)", "url": "https://wpnews.pro/news/jackpot-lab-10-broken-llm-apps-you-can-poke-at-in-your-browser", "canonical_source": "https://promptcube3.com/en/threads/4946/", "published_at": "2026-08-04 15:00:51+00:00", "updated_at": "2026-08-04 15:55:13.797491+00:00", "lang": "en", "topics": ["ai-safety", "ai-tools", "ai-agents"], "entities": ["hego.red/jackpot", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/jackpot-lab-10-broken-llm-apps-you-can-poke-at-in-your-browser", "markdown": "https://wpnews.pro/news/jackpot-lab-10-broken-llm-apps-you-can-poke-at-in-your-browser.md", "text": "https://wpnews.pro/news/jackpot-lab-10-broken-llm-apps-you-can-poke-at-in-your-browser.txt", "jsonld": "https://wpnews.pro/news/jackpot-lab-10-broken-llm-apps-you-can-poke-at-in-your-browser.jsonld"}}