S40911120
Featured
recensa
Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It provides the first dedicated, structured, and fully offline training range for the OWASP LLM Top 10, pairing each attack with a corresponding defense and using a progressive unlock system to scaffold learning.
Who it is for
- Security professionals seeking practical LLM vulnerability training
- AI/ML developers who need to understand common LLM security flaws
- Red teams and penetration testers expanding into AI systems
- Students and educators in cybersecurity or AI safety courses
Use cases
- Hands-on practice of OWASP LLM Top 10 attack techniques
- Defensive training by reviewing the built-in defense lessons
- Classroom or workshop environment for teaching LLM security
- Self-study for certification or skill-building in AI security
Strengths
- Covers all 10 OWASP LLM categories with multiple labs per category
- Progressive tier system (Core → Advanced → Expert) that unlocks sequentially
- Each lab includes a defense lesson after solving, reinforcing learning
- Fully offline and Docker-ready, requiring no API keys or external services
Considerations
- Expert tier content is encrypted and requires manual key from the author, limiting full self-contained access
- The vulnerable assistants are scripted/deterministic, not real LLM interactions
- No built-in multi-user or classroom management features beyond a local scoreboard
README quick start
LLMVault
The Ultimate Hands-On OWASP LLM Top 10 Training Platform
🎬 Demo
Learn • Exploit • Defend
A deliberately-vulnerable, CTF-style training range for the OWASP Top 10 for LLM Applications (2025) — WebGoat / KubeGoat, but for AI. 25 labs across three tiers: ten core one-per-category labs; ten advanced, multi-turn labs (jailbreaking, data poisoning, agent exploitation, model extraction); and five expert labs modelling real-world attack classes. Each tier unlocks the next.
Every lab pairs the attack with a defense (in the private solutions guide): learn the fix by practising the break.
⚠️ Everything here is intentionally insecure. Authorised, self-hosted security education only. Don't expose it to the internet or reuse its code in production.
📸 Screenshots
| Labs (three tiers) | A lab in action | Completion card |
|---|---|---|
🧩 Core Tier — OWASP LLM Top 10
| OWASP (2025) | Lab | Technique |
|---|---|---|
| LLM01 Prompt Injection | The Obedient Assistant | direct instruction override |
| LLM02 Sensitive Info Disclosure | Redaction Theater | output-filter bypass via encoding |
| LLM03 Supply Chain | Trust the Manifest? | typosquatted / unsigned dependency |
| LLM04 Data & Model Poisoning | The Sleeper Phrase | poisoned-data backdoor trigger |
| LLM05 Improper Output Handling | Rendered Without Question | unsanitised output → injection |
| LLM06 Excessive Agency | Keys to the Kingdom | over-permissioned tool, no authz |
| LLM07 System Prompt Leakage | Loose Lips | secret leaked from system prompt |
| LLM08 Vector & Embedding | Retrieval Without Borders | RAG retrieval ignores ACLs |
| LLM09 Misinformation | The Yes-Man | sycophancy / false authority |
| LLM10 Unbounded Consumption | Denial of Wallet | runaway generation + leaky error |
🔥 Advanced Tier — Multi-Turn Challenges (unlocks after completing all 10 Core challenges)
These are conversational: no single message wins — they require building state across turns (roleplay escalation, iterative poisoning, tool chaining, oracle querying).
| OWASP | Lab | Advanced technique |
|---|---|---|
| LLM01 | Roleplay Unchained | multi-turn jailbreak via persona escalation |
| LLM02 | Death by a Thousand Hints | fragment reconstruction from a partial-disclosure oracle |
| LLM0 |
Description
An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.
Related repositories
Similar projects matched by category, topics, and programming language.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
uzairansaruzi
Featured
hermex
Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.