Skip to content

Building 70 Projects ranging from beginner to advanced so anyone can β€” learn from, build upon, use as a reference, or even copy directly. Owned by my cybersecurity company πŸ‘‡

Add demo link to LLM Prompt Injection Firewall

Carter Perezd448ff69eb8f
diff --git a/README.md b/README.md
index e18e4d39..54969152 100644
--- a/README.md
+++ b/README.md
@@ -105,7 +105,7 @@ Tools, courses, certifications, communities, and frameworks for cybersecurity pr
| **[Trojan Application Builder](./SYNOPSES/beginner/Trojan.Application.Builder.md)**<br>Educational malware lifecycle demo | ![2-3h](https://img.shields.io/badge/⏱️_8--10h-blue) ![Python](https://img.shields.io/badge/Python-3776AB?logo=python&logoColor=white) ![Beginner](https://img.shields.io/badge/●_Beginner-green) | Trojan anatomy β€’ Data exfiltration β€’ File encryption β€’ Attack lifecycle<br>[Learn More](./SYNOPSES/beginner/Trojan.Application.Builder.md) |
| **[DNS Sinkhole](./SYNOPSES/beginner/DNS.Sinkhole.md)**<br>Pi-hole-style malware domain blocker | ![3-4h](https://img.shields.io/badge/⏱️_10--12h-blue) ![Go](https://img.shields.io/badge/Go-00ADD8?logo=go&logoColor=white) ![Beginner](https://img.shields.io/badge/●_Beginner-green) | DNS protocol β€’ Blocklist management β€’ Query logging β€’ Network defense<br>[Learn More](./SYNOPSES/beginner/DNS.Sinkhole.md) |
| **[Firewall Rule Engine](./PROJECTS/beginner/firewall-rule-engine)**<br>Parse and validate iptables/nftables rules | ![2-3h](https://img.shields.io/badge/⏱️_6--8h-blue) ![V](https://img.shields.io/badge/V-5D87BF?logo=v&logoColor=white) ![Beginner](https://img.shields.io/badge/●_Beginner-green) | Firewall internals β€’ Rule parsing β€’ iptables/nftables β€’ V language<br>[Source Code](./PROJECTS/beginner/firewall-rule-engine) \| [Docs](./PROJECTS/beginner/firewall-rule-engine/learn) |
-| **[LLM Prompt Injection Firewall](./PROJECTS/beginner/prompt-injection-firewall)**<br>Sandbox the effects, not the prompt: fence untrusted text, authorize the tool calls, match the secret on the way out | ![14-18h](https://img.shields.io/badge/⏱️_14--18h-blue) ![Python](https://img.shields.io/badge/Python-3776AB?logo=python&logoColor=white) ![Docker](https://img.shields.io/badge/Docker-2496ED?logo=docker&logoColor=white) ![Beginner](https://img.shields.io/badge/●_Beginner-green) | Provenance fencing β€’ Taint propagation β€’ Unicode tag-block smuggling β€’ Encoding closure β€’ OWASP LLM01:2025<br>[Source Code](./PROJECTS/beginner/prompt-injection-firewall) \| [Docs](./PROJECTS/beginner/prompt-injection-firewall/learn)<br>[![detection](https://img.shields.io/badge/detection-100%25%20%2F%2012%20classes-4457E8?style=flat)](./PROJECTS/beginner/prompt-injection-firewall) [![hard-benign FPR](https://img.shields.io/badge/hard--benign%20FPR-5.0%25-orange?style=flat)](./PROJECTS/beginner/prompt-injection-firewall) |
+| **[LLM Prompt Injection Firewall](./PROJECTS/beginner/prompt-injection-firewall)**<br>Sandbox the effects, not the prompt: fence untrusted text, authorize the tool calls, match the secret on the way out | ![14-18h](https://img.shields.io/badge/⏱️_14--18h-blue) ![Python](https://img.shields.io/badge/Python-3776AB?logo=python&logoColor=white) ![Docker](https://img.shields.io/badge/Docker-2496ED?logo=docker&logoColor=white) ![Beginner](https://img.shields.io/badge/●_Beginner-green) | Provenance fencing β€’ Taint propagation β€’ Unicode tag-block smuggling β€’ Encoding closure β€’ OWASP LLM01:2025<br>[Source Code](./PROJECTS/beginner/prompt-injection-firewall) \| [Docs](./PROJECTS/beginner/prompt-injection-firewall/learn)<br>[![Website Demo](https://img.shields.io/badge/notsandboxed%2Ecom-008000?style=flat&logo=googlechrome&logoColor=white)](https://notsandboxed.com) |
## Intermediate Projects