Usta0x001/Phantom
Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing
Leverages a ReAct (Reason–Act) loop to connect LLMs with 53 security tools in an isolated Docker sandbox, automatically chaining multi-step exploits and verifying findings with working proof-of-concept scripts. Integrates with LiteLLM for LLM abstraction, enriches all vulnerabilities with MITRE ATT&CK mappings and compliance tags (OWASP Top 10, PCI DSS, NIST 800-53), and maintains cross-scan memory to reduce false positives and adapt to target responses in real time.
104 stars.
Stars
104
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Usta0x001/Phantom"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Ed1s0nZ/CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security...
vxcontrol/pentagi
✨ Fully autonomous AI Agents system capable of performing complex penetration testing tasks
GH05TCREW/pentestagent
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty,...
SanMuzZzZz/LuaN1aoAgent
LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing...
asaotomo/FofaMap
FofaMap v2.0 是一款基于 Python3 开发的全网首个 AI 驱动红队资产测绘智能体。在延续原有 FOFA 数据采集、存活检测、统计聚合、图标 Hash...