hackmyagent
Active·★ 83·NOASSERTION·Updated 2026-10-21
HackMyAgent is a comprehensive security scanner and red-team toolkit designed for AI agents. It performs static and semantic checks, runs adversarial payloads, and simulates agent behavior to identify vulnerabilities.
#AI Security#Agent Hacking#Red Teaming#Vulnerability Scanner#Prompt Injection#Supply Chain Security#Static Analysis#Semantic Analysis
01
Features
01Extensive Static and Semantic Checks (323+ across 74 categories)
02Adversarial Payload Battery (164+ across 16 categories)
03Deep Behavioural Simulation with 20 probes
04Self-Securing Binary with integrity verification
05NanoMind AI Analyst for threat narratives and coverage escalations
02
Compatibility
Node.js
Runtime
Verified via docs
Homebrew
Package Manager
Verified via docs
npm
Package Manager
Verified via docs
03
Quick start
1
$ git clone https://github.com/opena2a-org/hackmyagent.git
2
$ cd hackmyagent
3
$ npm install
4
$ npm run build
04
Use cases
↳Scan your own AI agent projects for vulnerabilities
↳Red-team MCP servers to map attack surfaces
↳Integrate security checks into CI/CD pipelines
↳Audit shadow AI tools and governance gaps
↳Perform runtime protection and API traffic inspection
05
Alternatives
agent-security-scanner-mcp★ 124
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
hol-guard★ 963
AI antivirus for developer agents: protect Codex, Claude Code, Cursor, Gemini, OpenCode, plugins, skills, MCP servers, and AI harnesses before tools run.
mcptrustchecker★ 172
Security scanner for MCP (Model Context Protocol) servers — reads the real published npm/PyPI source, not just metadata, to catch tool poisoning, prompt injection, toxic flows & supply-chain risk. Offline, deterministic A–F Trust Score, SARIF + CI gates.
aguara★ 94
Security scanner for AI agent skills & MCP servers. 173 detection rules. 13 categories. 5 registries monitored daily. OpenClaw detection included. No API keys, no cloud, no LLM. One binary. Detection engine behind Oktsec.
cc-audit★ 26
AI-free static security scanner for Claude Code artifacts (Skills, Hooks, MCP configs). Detects data exfiltration, prompt injection, and supply chain risks with deterministic, reproducible results.
agentshield★ 21
🛡️ The security firewall for AI agent tools & MCP servers (Claude, GPT-5.6, Gemini 3.7, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.
Comments
Log in to leave a comment
No comments yet. Be the first!