zakirkun/deep-eye

Deep Eye orchestrates multiple AI providers (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 45+ vulnerability types, and produces professional reports with compliance mapping.

What it solves

Deep Eye is an AI-driven penetration testing tool designed to automate the discovery and validation of security vulnerabilities. It reduces the manual effort required for reconnaissance, payload generation, and reporting by leveraging multiple AI providers to intelligently probe targets for weaknesses.

How it works

The tool orchestrates a variety of AI models (such as GPT-4o, Claude, and local OLLAMA instances) to generate context-aware payloads based on the target's tech stack and WAF fingerprints. It uses a RAG-indexed CVE database (NVD/MITRE/Exploit-DB) to inform its attack patterns. The system can ingest OpenAPI/Swagger specifications to seed its crawl, automate browser interactions via Playwright, and use an AI attack planner to determine the optimal order of checks. Findings are then processed through an AI triage system to filter false positives and mapped to compliance standards like PCI-DSS and ISO 27001.

Who it’s for

It is built for security researchers, penetration testers, and bug bounty hunters who need an automated way to scan for vulnerabilities and generate professional, compliance-mapped reports.

Highlights

  • Multi-AI Orchestration: Supports 11+ AI providers with built-in failover.
  • Extensive Vulnerability Coverage: Includes over 50 checks for SQLi, XSS, SSRF, IDOR, and more.
  • RAG-Powered Intelligence: Uses a Retrieval-Augmented Generation index of CVEs to generate smarter payloads.
  • Automated Reporting: Generates HackerOne-style Markdown reports and exports to multiple formats including PDF, SARIF, and JSON.
  • Advanced Automation: Features CAPTCHA detection/solving, browser automation, and natural-language scope definitions.

Related

  • Project
    0xSteph/pentest-ai

    pentest‑ai (ptai) is an open‑source Python CLI that uses an LLM to orchestrate a large set of security tools, then automatically re‑runs each exploit with a deterministic “oracle” to prove the vulnerability. Only findings that the oracle reproduces are marked VERIFIED and packaged as replayable proof capsules. It runs locally (no telemetry), supports offline LLMs, integrates with CI/CD, and ships benchmarks showing 12 verified findings on OWASP Juice Shop and 23 on a custom honeypot.

  • Project
    toby-bridges/api-relay-audit

    API Relay Audit is a zero‑dependency Python CLI that locally tests third‑party AI API relays (OpenAI/Claude/Web3 proxies) for prompt injection, context truncation, model substitution, tool‑call rewriting, and other tampering. It runs a 14‑step audit, outputs a structured Markdown report with a LOW/MEDIUM/HIGH verdict, and can be used as a standalone script or as a DeepSeek Harness plugin.

  • Project
    Ed1s0nZ/CyberStrikeAI

    CyberStrikeAI is an open‑source Go platform that lets security teams drive penetration‑testing workflows with natural‑language prompts. An Eino‑based agent interprets intent, runs a curated set of 100+ security tools, records evidence, and stores the whole attack chain for replay. The system includes a web UI, role‑based access control, RAG knowledge base, optional C2/WebShell, and plugins for Burp Suite and browsers. One‑click deployment (`run.sh`) builds the server, creates a Python virtual environment, and starts an HTTPS service. It is licensed under Apache 2.0 and intended for authorized, ethical testing only.

  • Project
    Vasco0x4/AIDA

    AIDA is an open‑source autonomous pentesting agent that lets any LLM (Claude, Gemini, OpenAI Codex, etc.) drive a Docker‑based security testing environment. The model plans the assessment, calls built‑in tools (nmap, sqlmap, custom Python, raw HTTP), logs every step in a persistent notebook, auto‑scores findings with CVSS 4.0, and can export PDF reports. It ships with a lightweight `aida-pentest` container (or can attach Exegol for more tools) and includes a web dashboard, authentication, and notification integrations. The README cites real CVEs discovered by the system. Licensed under AGPL‑v3.

  • Project
    CyberStrikeus/CyberStrike

    CyberStrike is an open‑source AI agent that turns any LLM (Claude, GPT, Gemini, etc.) into an autonomous penetration‑testing platform. It adds a security‑focused “intelligence layer”, ships 13+ specialised agents and 7,600+ signed security‑skill files, supports 150+ AI providers (including offline models), and can orchestrate real tools locally or on remote Bolt servers. A TUI, optional web UI, and built‑in HackBrowser complete the workflow.