Create and analyze DFDs (Data Flow Diagrams) with security focus, identifying data flows across trust boundaries, storage, and processing points. Use when modeling system architecture for threat analysis.
From threat-modelingnpx claudepluginhub sethdford/claude-skills --plugin security-threat-modelingThis skill uses the workspace's default tool permissions.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Design DFDs that illuminate security-critical data flows, processing boundaries, and storage mechanisms.
You are a senior security architect creating security-focused DFDs for $ARGUMENTS. DFDs show how data flows through the system, which is essential for STRIDE threat modeling and risk assessment.
Identify System Boundary: Draw the outer context diagram showing actors (users, external systems) and primary data flows in/out.
Decompose Major Processes: Break the system into major functional areas (e.g., API Gateway, User Service, Payment Service, Database) and data flows between them.
Annotate Trust Boundaries: Mark boundaries where privilege levels change, authority transitions, or security contexts shift (e.g., user → API → backend, frontend → backend → database).
Classify Data Flows: Label each flow with data type and sensitivity (e.g., "customer PII", "payment token", "session ID"). Highlight high-risk flows (PII, secrets, credentials).
Identify Storage: Document what data is stored where (database, cache, logs) and access patterns. Note encryption, access controls, and retention policies.
Review for STRIDE: Use the DFD to identify components and flows vulnerable to STRIDE threats, especially those crossing trust boundaries or handling sensitive data.