Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
agent
Agentic offensive-security in your terminal
252stars
26forks
TypeScript
aiai-agentsbugbountypenetration-testingsecurity-auditsecurity-automation
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
CLI agent that helps security engineers run authorized penetration tests with real tools, human approvals, and audit-ready findings.
Use this when
- running a new authorized pentest engagement
- testing a web app for IDOR or broken access control
- reconciling findings with evidence from curl logs
- resuming a paused assessment with saved context
- validating a suspected SSRF or JWT flaw
Don't use when
- unauthorized testing (use only with explicit permission)
- blindly trusting AI-generated findings without evidence
- automated exploitation without human oversight
Capabilities
- human-in-the-loop CLI with slash commands
- built-in pentest skills for web vulns, SSRF, SSTI, JWT, etc.
- curl-first execution with reproducible commands
- session memory and context snapshots for long engagements
- Burp Suite integration for traffic capture and analysis
- Markdown findings with PoC, impact, and remediation
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest PentesterFlow/agentAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/agent curl -fsSL https://raw.githubusercontent.com/PentesterFlow/agent/main/SKILL.md -o ~/.claude/skills/agent/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
agent — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt