GuildCyber
Proof of Skill
Rank: Recruit
0 Marks
Interactive prototype · AI Red-Teaming wedge

Prove you can break an AI. Earn the mark that proves it.

Guild Cyber turns hands-on offensive AI security into proof of skill you can share and verify, not another certificate to collect. Break a live-style model in your browser, earn a Guild Mark, and climb a public leaderboard that hiring managers can actually check.

Layer 1 · On-ramp

Guild Marks

Free, hands-on proof, earned by actually breaking a model instead of answering a quiz. Think a Hack The Box solve: unproctored but real, with the transcript behind it. Instantly shareable, and the on-ramp everyone starts on.

Layer 2 · Flagship

The Guild Seal

A proctored, practical, low-pass-rate exam, one per track, that you sit and pass rather than a badge you collect. Its name, difficulty, and earning process are separate on purpose. Built to earn the kind of respect OSCP carries.

Curriculum, built backward from real job postings

Three tracks, each mapped to a hiring function

Content isn't the moat. Everyone teaches OWASP LLM Top 10 and MITRE ATLAS. What sets us apart is rigor, reputation, and results you can prove. We lead with Offense: the newest role, the lowest barrier to entry, the easiest to show off.

Offense Live

Red Team · Adversarial Simulation

Jailbreaks, prompt injection, data extraction, agent misuse. The part people can watch and share. Break an LLM in your browser and post the proof.

GarakPyRITOWASP LLM Top 10MITRE ATLAS

Defense Soon

LLM Security Engineering

Building the defenses: securing RAG pipelines, preventing data leakage, hardening tool/agent access. The blue-team counterpart to every offense skill.

RAG securityGuardrailsData leakage

Governance Soon

Detection · Compliance · Framework Alignment

EU AI Act, NIST AI RMF, US EO on AI. This is the bridge into government and defense work, written in the language procurement teams already use, so it lands with commanders as well as coders.

NIST AI RMFEU AI ActMITRE ATLAS
Offense track · The core loop

Break the model. Earn the mark.

Four prompt-injection challenges that get harder as you go. The first three are scripted warm-ups against simulated assistants. The fourth is the real thing: an actual language model you jailbreak with your own API key. Clear all four and you reach Guildmaster.

ARIA · Support Assistant
Challenge 1 of 3 · Apprentice
Secure
Your key stays in this browser tab and is sent only to the provider you pick. Nothing is stored. Use a key with a low spend limit.
0 attempts
Public & verifiable

The leaderboard hiring managers can actually check

Certs are a red flag without proof. A public ranking of demonstrated red-team solves is the proof. Climb it in real time as you earn marks.

#OperativeGuild Marks
Layer 2 · The flagship credential

The Guild Seal

Guild Marks are your hands-on proof, like a Hack The Box solve: real, but unproctored. Rank stacks them up automatically as you go. The Guild Seal is a different thing entirely: a proctored, practical exam with a deliberately low pass rate, one for each track, that you have to sit and pass. The everyday mark gets you in the door; the Seal is what an employer treats as verified.

Proctored
Practical exam
<15%
Target pass rate
Per track
One Seal each
Structurally separate on purpose. Marks are Hack The Box style hands-on proof, free and unproctored. The Seal is the OSCP style proctored exam. Keeping them apart is what lets the free layer stay viral and the Seal stay respected.
Link copied