CHYing-agent
Autonomous AI agent for solving CTF and penetration testing challenges
All Skills in This Repository (17)
Pure Emerald Level Indicatorsrce
Automate detection and exploitation workflows for remote code execution vulnerabilities.
ssrf
Detect and exploit server-side request forgery vulnerabilities in URL parameters.
sqli
Automate SQL injection detection and exploitation across UNION, error-based, blind, and stacked queries.
web-recon
Enumerate web attack surfaces with curl, dirsearch, gobuster, ffuf, nmap, and whatweb.
xss
Detect and test reflected, stored, and DOM-based XSS vulnerabilities.
auth-bypass
Detect and exploit authentication and authorization bypasses in API endpoints.
file-inclusion
Test local and remote file inclusion vulnerabilities through payloads and protocols.
stagnation-recovery
Diagnoses agent stagnation patterns and redirects security testing toward untried attack surfaces.
cryptography
Solves CTF cryptography challenges by dispatching cipher identification to attack modules with runnable exploit templates.
forensics-misc
Analyze disk images, memory dumps, network captures, and steganography files to solve CTF forensics challenges.
binary
Analyze and exploit CTF binary challenges using Ghidra, pwntools, and dynamic debugging.
ctf-postmortem
Analyzes CTF challenge logs to compute solve rates and diagnose systemic failure root causes.
Frequently Asked Questions
FAQPage SchemaHow to install CHYing-agent?βΌ
Run `npx skills add yhy0/CHYing-agent --all -g -y` in your terminal to install all skills in this suite globally.
What does CHYing-agent do?βΌ
It is an autonomous agent that solves CTF and penetration testing challenges, covering web exploits, binary pwn, cryptography, forensics, cloud attacks, and AI prompt injection.
Which CTF categories does it cover?βΌ
It ships skills for web security, binary exploitation and reverse engineering, cryptography, forensics and misc, infrastructure and cloud exploitation, and AI security prompt injection.
Does CHYing-agent work with Claude Code?βΌ
Yes. All skills follow the standard SKILL.md format and run inside Claude Code and compatible agent runtimes with MCP tool support.
Can it keep working after context limits?βΌ
Yes. Its ProgressCompiler and handoff files let the agent resume long challenges after context compaction without losing prior findings or dead ends.
Related Repositories in Software Engineering
View All in Software Engineeringβopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core