> ## Content Index > Fetch the complete content index at: https://darkwebinformer.com/llms.txt > Use this file to discover other available public pages before exploring further. # PentestAgent: An AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows - URL: https://darkwebinformer.com/pentestagent-an-ai-agent-framework-for-black-box-security-testing-supporting-bug-bounty-red-team-and-penetration-testing-workflows/ - Published: 2025-12-29T18:43:48.000Z - Updated: 2025-12-29T18:43:48.000Z - Author: Dark Web Informer - Tags: Tools --- GitHub: --- # PentestAgent [](https://github.com/GH05TCREW/pentestagent#pentestagent) ### AI Penetration Testing 0:00 /1:00 1× ## Requirements [](https://github.com/GH05TCREW/pentestagent#requirements) - Python 3.10+ - API key for OpenAI, Anthropic, or other LiteLLM-supported provider ## Install [](https://github.com/GH05TCREW/pentestagent#install)\# Clone git clone https://github.com/GH05TCREW/pentestagent.git cd pentestagent \# Setup (creates venv, installs deps) .\\scripts\\setup.ps1 # Windows ./scripts/setup.sh # Linux/macOS \# Or manual python -m venv venv .\\venv\\Scripts\\Activate.ps1 # Windows source venv/bin/activate # Linux/macOS pip install -e ".\[all\]" playwright install chromium # Required for browser tool ## Configure [](https://github.com/GH05TCREW/pentestagent#configure) Create `.env` in the project root: ``` ANTHROPIC_API_KEY=sk-ant-... PENTESTAGENT_MODEL=claude-sonnet-4-20250514 ``` Or for OpenAI: ``` OPENAI_API_KEY=sk-... PENTESTAGENT_MODEL=gpt-5 ``` Any [LiteLLM-supported model](https://docs.litellm.ai/docs/providers) works. ## Run [](https://github.com/GH05TCREW/pentestagent#run)pentestagent # Launch TUI pentestagent -t 192.168.1.1 # Launch with target pentestagent --docker # Run tools in Docker container ## Docker [](https://github.com/GH05TCREW/pentestagent#docker) Run tools inside a Docker container for isolation and pre-installed pentesting tools. ### Option 1: Pull pre-built image (fastest) [](https://github.com/GH05TCREW/pentestagent#option-1-pull-pre-built-image-fastest)\# Base image with nmap, netcat, curl docker run -it --rm \\ \-e ANTHROPIC\_API\_KEY=your-key \\ \-e PENTESTAGENT\_MODEL=claude-sonnet-4-20250514 \\ ghcr.io/gh05tcrew/pentestagent:latest \# Kali image with metasploit, sqlmap, hydra, etc. docker run -it --rm \\ \-e ANTHROPIC\_API\_KEY=your-key \\ ghcr.io/gh05tcrew/pentestagent:kali ### Option 2: Build locally [](https://github.com/GH05TCREW/pentestagent#option-2-build-locally)\# Build docker compose build \# Run docker compose run --rm pentestagent \# Or with Kali docker compose --profile kali build docker compose --profile kali run --rm pentestagent-kali The container runs PentestAgent with access to Linux pentesting tools. The agent can use `nmap`, `msfconsole`, `sqlmap`, etc. directly via the terminal tool. Requires Docker to be installed and running. ## Modes [](https://github.com/GH05TCREW/pentestagent#modes) PentestAgent has three modes, accessible via commands in the TUI: | Mode | Command | Description | | ------ | ------------- | ---------------------------------------------------------- | | Assist | (default) | Chat with the agent. You control the flow. | | Agent | /agent | Autonomous execution of a single task. | | Crew | /crew | Multi-agent mode. Orchestrator spawns specialized workers. | ### TUI Commands [](https://github.com/GH05TCREW/pentestagent#tui-commands) ``` /agent Run autonomous agent on task /crew Run multi-agent crew on task /target Set target /tools List available tools /notes Show saved notes /report Generate report from session /memory Show token/memory usage /prompt Show system prompt /clear Clear chat and history /quit Exit (also /exit, /q) /help Show help (also /h, /?) ``` Press `Esc` to stop a running agent. `Ctrl+Q` to quit. ## Playbooks [](https://github.com/GH05TCREW/pentestagent#playbooks) PentestAgent includes prebuilt **attack playbooks** for black-box security testing. Playbooks define a structured approach to specific security assessments. **Run a playbook:** pentestagent run -t example.com --playbook thp3\_web 0:00 /0:20 1× ## Tools [](https://github.com/GH05TCREW/pentestagent#tools) PentestAgent includes built-in tools and supports MCP (Model Context Protocol) for extensibility. **Built-in tools:** `terminal`, `browser`, `notes`, `web_search` (requires `TAVILY_API_KEY`) ### MCP Integration [](https://github.com/GH05TCREW/pentestagent#mcp-integration) Add external tools via MCP servers in `pentestagent/mcp/mcp_servers.json`: { "mcpServers": { "nmap": { "command": "npx", "args": \["-y", "gc-nmap-mcp"\], "env": { "NMAP\_PATH": "/usr/bin/nmap" } } } } ### CLI Tool Management [](https://github.com/GH05TCREW/pentestagent#cli-tool-management)pentestagent tools list # List all tools pentestagent tools info # Show tool details pentestagent mcp list # List MCP servers pentestagent mcp add \[args...\] # Add MCP server pentestagent mcp test # Test MCP connection ## Knowledge [](https://github.com/GH05TCREW/pentestagent#knowledge) - **RAG:** Place methodologies, CVEs, or wordlists in `pentestagent/knowledge/sources/` for automatic context injection. - **Notes:** Agents save findings to `loot/notes.json` with categories (`credential`, `vulnerability`, `finding`, `artifact`). Notes persist across sessions and are injected into agent context. - **Shadow Graph:** In Crew mode, the orchestrator builds a knowledge graph from notes to derive strategic insights (e.g., "We have credentials for host X"). ## Project Structure [](https://github.com/GH05TCREW/pentestagent#project-structure) ``` pentestagent/ agents/ # Agent implementations config/ # Settings and constants interface/ # TUI and CLI knowledge/ # RAG system and shadow graph llm/ # LiteLLM wrapper mcp/ # MCP client and server configs playbooks/ # Attack playbooks runtime/ # Execution environment tools/ # Built-in tools ``` ## Development [](https://github.com/GH05TCREW/pentestagent#development)pip install -e ".\[dev\]" pytest # Run tests pytest --cov=pentestagent # With coverage black pentestagent # Format ruff check pentestagent # Lint ## Legal [](https://github.com/GH05TCREW/pentestagent#legal) Only use against systems you have explicit authorization to test. Unauthorized access is illegal. ## License [](https://github.com/GH05TCREW/pentestagent#license) MIT