AISecurityLab/hackagent
HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents
This toolkit helps security researchers and AI safety practitioners find weaknesses in their AI agents. It takes your AI agent (like a chatbot or automated system) and tests it with known attack techniques such as prompt injection and jailbreaking. The output is a report detailing any vulnerabilities found, allowing you to strengthen your AI's defenses. It's designed for those responsible for ensuring AI system security.
Use this if you need to proactively identify security vulnerabilities in your AI agents before they can be exploited in production.
Not ideal if you're looking for a general-purpose AI development framework or a tool to analyze standard software application security.
Stars
37
Forks
4
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/AISecurityLab/hackagent"
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...
GH05TCREW/pentestagent
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty,...
vxcontrol/pentagi
✨ Fully autonomous AI Agents system capable of performing complex penetration testing tasks
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...
SanMuzZzZz/LuaN1aoAgent
LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing...