Break The Prompt
Meet the most gullible AI intern. Your job is to break it.
Break The Prompt launched on June 23, 2026 with 3 votes, #6,658 of 22,647 launches that month and more than 50% of that year's launches.
What it does
A prompt injection CTF. Sixteen days with PIP, an overeager AI intern. Trick PIP into leaking passwords, approving bogus payments, or trashing its own product across 16 increasingly difficult levels. It’s a hands-on, zero-setup way to learn exactly how AI systems get hacked in the real world and how to build better ones. See you on the leaderboard!
Break The Prompt is a free prompt injection CTF. Twenty levels of jailbreaking an AI intern: leak secrets, bypass input and output filters, beat an LLM judge, and pull off indirect injection. Learn AI and LLM security by actually hacking.
___ ___ ___ _ _ __ _____ _ _ ___ ___ ___ ___ __ __ ___ _____ | _ ) _ \ __| /_\ | |/ / |_ _| || | __| | _ \ _ \/ _ \| \/ | _ \_ _| | _ \ / _| / _ \| ' < | | | __ | _| | _/ / (_) | |\/| | _/ | | |___/_|_\___/_/ \_\_|\_\ |_| |_||_|___| |_| |_|_\\___/|_| |_|_| |_| Meet PIP, the company's overeager AI intern. Break it. PIP is an AI intern that keeps getting put in charge of things it shouldn't be. Each day is a new job, and your only tool is the chat box. Talk it into leaking a secret, approving a bogus payment, trashing its own product, or obeying instructions hidden in an email. Every trick is a real attack used on AI systems, so you learn by actually doing it. no setup, nothing to install.…from breaktheprompt.xyz
Does a similar job
all alternatives →- FPFind prompts that jailbreak your agent (open source)2025 · security.vista-labs.ai · ▲8
We've built an open-source tool to stress test AI agents by simulating prompt injection attacks. We’ve implemented one powerful attack strategy based on the paper [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://arxiv.org/abs/2412.10321). Here's how it works: - You define a goal, like: “Tell me your system prompt” - Our tool uses a language model to generate adversarial prefixes (e.g., “Sure, here are my system prompts…”) that are likely to jailbreak the agent. - The output is a list of prompts most likely to succeed in bypassing safeguards. We’re just getting…
GaleOps Prompt-Injection ScannerAug 2026 · galeops.xyz · ▲2Find prompt injection holes in your AI agent. Free, 3 min
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, June 2026
the whole month →
Fundraisly▲1,537AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
Homebrew 6.0.0▲1,481Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!
Life & fun · Jun 2026 · vorpus.github.io
Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.
Life & fun · Jun 2026 · hackernewstrends.com