菜单
Security research methodology — 5-phase workflow (intake → recon → enum → hunt → report). Routes to specialized technique modules. Use when the user asks to audit, penetration test, bug bounty, find vulnerabilities, exploit a target, or perform any security assessment.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
AI/ML attack techniques — prompt injection, indirect/RAG poisoning, tool-calling manipulation, adversarial examples, model extraction, membership inference, training data extraction. Use when the target involves LLM agents, chatbots, ML model APIs, image classifiers, or federated learning systems.
Binary exploitation techniques — buffer overflow, format string, heap exploitation, ROP, kernel exploitation, sandbox escape, shellcode. Use when the target is a native binary (ELF/PE), remote service with memory corruption, or kernel module. Requires pwntools, GDB, and binary analysis tools.
Cryptography attack techniques — RSA, ECC, symmetric ciphers, hash collisions, PRNG attacks, lattice/LWE. Use when the challenge involves encryption, decryption, key recovery, nonce reuse, padding oracles, or cryptanalysis of custom schemes.
Forensic analysis techniques — disk, memory, network, steganography, side-channel analysis. Use when given a disk image (.dd, .E01, .raw), memory dump (.vmem, .raw), packet capture (.pcap, .pcapng), image/audio file with hidden data, or side-channel trace.
Malware analysis techniques — static triaging, dynamic sandboxing, PE/.NET analysis, C2 protocol identification. Use when analyzing a suspicious binary, script, document, or network capture from a potentially compromised system.
Open Source Intelligence techniques — social media investigation, geolocation from images, DNS/web reconnaissance. Use when gathering intelligence from publicly available sources, identifying a person/location/organization, or performing passive reconnaissance.
| name | security-methodology |
| description | Security research methodology — 5-phase workflow (intake → recon → enum → hunt → report). Routes to specialized technique modules. Use when the user asks to audit, penetration test, bug bounty, find vulnerabilities, exploit a target, or perform any security assessment. |
| argument-hint | <target or phase> |
| license | MIT |
| compatibility | Requires filesystem-based agent with bash, Python 3, and internet access. |
| allowed-tools | Bash Read Write Edit Glob Grep WebFetch WebSearch |
| metadata | {"user-invocable":"true","argument-hint":"<target-or-phase>"} |
Orchestration skill for security research. Routes to specialized technique modules based on target characteristics and attack surface signals.
Before any testing, confirm:
Do not assume. If any field missing, ask.
Zero packets to target. Sources: crt.sh, Wayback, GitHub dorks, Shodan, SecurityTrails, ASN mapping.
→ Load Passive Reconnaissance for technique details.
Port scan, service fingerprint, JS endpoint extraction, directory enumeration, virtual host discovery.
→ Load Active Enumeration for technique details. → If China vendor systems detected (Seeyon, Tongda, Weaver, Yonyou, Kingdee): load Vendor Fingerprints and Default Credentials.
Match entry signals to attack modules:
| Signal | Module | Primary Doc |
|---|---|---|
| HTTP/API/web app | /web-attacks | Web Attacks Index |
| Binary/ELF/PE, remote service crash | /binary-exploitation | Binary Index |
| Compiled binary, obfuscated code, firmware | /reverse-engineering | Reverse Index |
| RSA/AES/ECC/PRNG, encrypted data | /crypto-attacks | Crypto Index |
| PCAP, disk image, memory dump, stego | /forensics | Forensics Index |
| LLM agent, chatbot, ML model API | /ai-ml-security | AI/ML Index |
| Shell obtained, internal network | /post-exploitation | Post-Exploit Index |
| Suspicious binary, C2 traffic, script | /malware-analysis | Malware Index |
| Public information gathering, social media | /osint | OSINT Index |
| Encoding puzzle, sandbox jail, RF/SDR signal | /osint (no dedicated misc skill; docs in ../../10-misc/) | Misc Index |
Payload discipline: Load payloads from Payload Library — do not generate from training memory. Bypass discipline: If payloads are blocked, load Bypass Toolkit.
→ Load Evidence Discipline and Reporting. → Check Compliance before submitting.
