Skills
.Work. You
Rest

threat-modeling-llm-app

Community

Build auditable threat models for LLM apps.

Software Engineering#threat modeling#stride#prompt injection#llm security#rag security#owasp llm
Authorrocklambros
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps you analyze an LLM-powered application before deployment so you can identify threats, trust boundaries, and residual risks instead of discovering them after launch.

Core Features & Use Cases

  • Catalog-driven analysis: Works against a user-supplied threat catalog such as OWASP LLM Top 10, MITRE ATLAS, or a custom internal register.
  • Boundary and component inventory: Maps prompts, retrievers, tools, and output sinks into a clear trust-boundary diagram.
  • Structured threat register: Produces STRIDE-classified findings with likelihood, impact, mitigations, owners, and coverage gaps for review or audit.
  • Use cases: Reviewing a chatbot, RAG system, completion API, summarization pipeline, or any other LLM-backed product before release.

Quick Start

Analyze my LLM application with the catalog I provide and produce a threat register with trust boundaries, STRIDE classifications, mitigations, and top residual risks.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: threat-modeling-llm-app
Download link: https://github.com/rocklambros/rcs/archive/main.zip#threat-modeling-llm-app

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.