菜单
Security payload reference — SQL injection, XSS, SSRF, command injection, SSTI, file inclusion, JWT, deserialization, WAF bypass, binary exploitation, and post-exploitation payloads. Load specific payload files by category. NEVER generate payloads from memory — always reference this library.
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
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.
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.
| name | payload-reference |
| description | Security payload reference — SQL injection, XSS, SSRF, command injection, SSTI, file inclusion, JWT, deserialization, WAF bypass, binary exploitation, and post-exploitation payloads. Load specific payload files by category. NEVER generate payloads from memory — always reference this library. |
| license | MIT |
| compatibility | Requires filesystem-based agent with read access to the payloads directory. |
| allowed-tools | Bash Read Glob Grep |
| metadata | {"user-invocable":"true","argument-hint":"<payload-type>"} |
Rule: Payloads come from files, not from training memory. Before using any payload, read the corresponding file.
| Category | Document | Lines |
|---|---|---|
| SQLi, NoSQLi, XSS, RCE, SSRF, SSTI, LFI, XXE, JWT, GraphQL, deserialization, smuggling, upload, traversal, prototype pollution, WebSocket | Web Payloads | 1,348 |
| Buffer overflow, format string, shellcode, ROP chains, heap, kernel, seccomp | Binary Payloads | 556 |
| Port scanning, SMB/AD/Kerberos, LLMNR, MITM, protocol attacks, tunneling, ADCS | Network Payloads | 491 |
| SQLi, XSS, RCE, SSRF, SSTI, LFI, JWT, Log4j, Spring, Fastjson, Struts2, WebLogic, ThinkPHP, Shiro, Tomcat, Laravel bypasses | WAF Bypass | 736 |
1. Identify attack type from target signal
2. Read the corresponding payload file
3. Select payload matching the target technology stack
4. If blocked, read WAF Bypass file for evasion variants
5. Document which payload worked and the target context
# Search for payloads matching a specific technology
grep -i "mysql" payloads/web/index.md
grep -i "nginx" payloads/waf-bypass.md
# Find all payloads for a specific vulnerability class
grep -A5 "### SQL Injection" payloads/web/index.md
grep -A5 "### XSS" payloads/web/index.md