
DeepTrap
Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

A CI/CD Red Team Framework for demonstrating Build Pipeline security risks.

Autonomous security research framework integrating static analysis, binary analysis, fuzzing, LLM-powered vulnerability validation, exploit…

OWASP Autonomous Penetration Testing Standard

Panthera(P.)uncia - Official CLI utility for Subdomain Center & Exploit Observer.

A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.

Arcane is a simple script designed to backdoor iOS packages (iphone-arm) and create the necessary resources for APT repositories.

LD_PRELOAD-based tool that hijacks gcc to inject malicious code into binaries during linking, enabling stealthy backdoor deployment without source…

Lightweight CLI tool that runs AI coding agents inside isolated Bubblewrap sandboxes with strict filesystem, network, and credential isolation to…

Hands-on CI/CD pipeline security workshop with Terraform lab, AWS exploitation, Kubernetes escape, and artifact backdooring exercises for offensive…

Hands-on capture-the-flag lab for the OWASP Kubernetes Top 10 (2025). Exploit 11 real-world cluster weaknesses, capture flags, then apply fixes and…

Sigma detection rules for AI agent security monitoring

Generate malicious files using recently published homoglyphic-attack (CVE-2021-42694)

Kernel-level security engine using eBPF-LSM to enforce file access policies based on process lineage, protecting sensitive data from supply-chain…

Security for the modern age of AI: defend against bad AI agents and malicious npm packages

Generate malicious files using recently published bidi-attack (CVE-2021-42574)

Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

CVE-2024-24590 ClearML RCE&CMD POC