菜单
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.
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 | osint |
| description | 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. |
| license | MIT |
| compatibility | Requires filesystem-based agent with bash, Python 3, curl, and internet access. |
| allowed-tools | Bash Read Write Edit Glob Grep WebSearch WebFetch |
| metadata | {"user-invocable":"true","argument-hint":"<target or image-path>"} |
| Target | Document |
|---|---|
| Social media accounts, usernames, profile analysis, Unicode steganography | Social Media |
| Image location, EXIF, reverse image search, satellite analysis, maps | Geolocation |
| DNS records, WHOIS, SSL certificates, Wayback Machine, Google dorks, Shodan | DNS & Web Recon |
# EXIF data
exiftool image.jpg | grep -iE '(GPS|Location|Date|Camera|Make)'
# Reverse image search (describe approach, do not automate)
# - Google Lens: upload or search by URL
# - Yandex: better for CIS/Asia
# - TinEye: oldest index
# - Baidu: China-specific images
# What to look for in the image:
# - Road signs, license plates, business names, phone numbers
# - Architecture style, vegetation, climate indicators
# - Street markings, driving side, power outlets
# - Language on signs, advertisements, product labels
# All records
dig ANY target.com
# Zone transfer (rare)
dig AXFR target.com @ns1.target.com
# Specific records
dig A target.com && dig AAAA target.com
dig MX target.com && dig TXT target.com
dig CNAME www.target.com
# Subdomain enumeration
for sub in $(cat subdomains.txt); do
host "$sub.target.com" 2>/dev/null | grep -E "has (IPv6 )?address"
done
site:target.com filetype:pdf confidential
site:target.com intitle:"index of"
site:target.com inurl:admin
site:target.com ext:sql | ext:bak | ext:old
site:github.com "target.com" password OR secret OR api_key