mrwadams/stride-gpt

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.

What it solves

STRIDE GPT is an AI-powered threat modeling tool designed to automate the identification of security threats and the creation of attack trees. It helps security professionals and developers identify vulnerabilities in applications—including traditional software, Generative AI, and Agentic AI systems—by applying the STRIDE methodology and mapping findings to industry standards like MITRE ATT&CK and ATLAS.

How it works

The tool uses Large Language Models (LLMs) to analyze application details provided by the user. It can operate in two primary modes: a single-shot analysis from a written description (/quick) or an autonomous agentic analysis of a codebase (/analyze). It supports multi-modal inputs, allowing users to upload architecture diagrams or use an embedded draw.io editor to provide structural context. The system then generates threat models, suggests mitigations, calculates DREAD risk scores, and produces Gherkin test cases.

Who it’s for

It is designed for security engineers, architects, and developers who need to perform comprehensive threat modeling and risk assessment for their applications, particularly those integrating frontier AI technologies.

Highlights

  • Agentic Codebase Analysis: An autonomous agent that plans, explores, and synthesizes threats across a codebase.
  • AI-Specific Threat Modeling: Integrated support for OWASP Top 10 for LLMs and the OWASP Top 10 for Agentic Applications (ASI).
  • Standardized Mapping: Automatically annotates threats with MITRE ATT&CK and ATLAS technique IDs.
  • Multi-Modal Input: Supports architecture diagrams, flowcharts, and an integrated draw.io editor to extract system components and trust boundaries.
  • Flexible Output: Generates reports in Markdown, JSON, SARIF, and self-contained HTML formats.
  • Broad Model Support: Compatible with OpenAI, Anthropic, Google, Mistral, and local models via LiteLLM.

Related

  • Project
    WecoAI/aideml

    AIDE ML is an open‑source Python library that implements an LLM‑guided tree‑search agent for automatically writing, debugging, and optimizing machine‑learning pipelines. Users describe a dataset, a goal, and an evaluation metric in natural language; the agent iteratively generates code, evaluates it, and prunes the search tree until the metric is maximized. The package includes a CLI, a Streamlit UI, HTML visualisation, and works with any OpenAI‑compatible LLM (including local Ollama models).

  • Project
    mukul975/Anthropic-Cybersecurity-Skills

    A library of 818 structured cybersecurity skills and playbooks designed to give AI agents the domain knowledge and decision-making workflows of a senior security analyst.

  • 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.

  • Project
    tophant-ai/aibeat

    A security evaluation framework for generative AI that provides evidence-based safety testing for LLMs, RAG apps, and AI agents.

  • Project
    Unclecheng-li/DeepSec

    An AI security platform combining a three-layer code auditing system (Shield) and an automated, authorized penetration testing engine (Spear).