AI-driven pentest agent,
with a built-in multi-engine arsenal.
aiscan combines LLM agents with traditional security scanning engines — port discovery, web probing, credential testing, POC execution and sensitive-information scanning in one statically linked binary with zero dependencies.
# no LLM needed — one-line scan $ aiscan scan -i 192.168.1.0/24 # with LLM — autonomous assessment $ aiscan agent -p "scan targets and check for high-risk vulnerabilities" \ -i 192.168.1.0/24 --api-key sk-... --model deepseek-chat
One binary, nine engines
◉gogo
Port, service and banner discovery in massive networks.
◉spray
Web probing, HTTP fingerprinting, path discovery and crawling.
◉zombie
Credential testing against discovered services.
◉neutron
Template-based POC execution engine.
◉proton
Sensitive-information scanning — API keys, tokens, secrets.
◉cyberhub
Fingerprint and POC association lookup.
◉arsenal
Security tool package manager, one-command installs.
◉web_search
CVE search and URL fetching for triage.
◉proxy
Multi-protocol proxy chains: trojan, vless, anytls, hy2, ss.
Three operating modes
→Scan
Deterministic multi-stage pipeline: port discovery → web probing → weak credentials → POC detection. No LLM required.
→Agent
Natural-language autonomous assessment with goal evaluation, automatic retries and a full interactive REPL.
→IOA
Internet of Agents — multi-agent distributed collaboration over shared message spaces with token authentication.
$ aiscan web --addr 0.0.0.0:8080 --token ■■■■