Skill Threat Modeling

Threat Modeling Skill v3.1.0

AI-native automated software risk analysis skill. LLM-driven, Code-First approach for comprehensive security risk assessment, threat modeling, security analysis, security audit, and penetration testing.

What's New in v3.1.0

• Comprehensive code quality audit and optimization to better align with current skill specifications
• Significantly enhanced agent and skill security analysis and assessment capabilities
• Full OWASP MCP Top 10 (2025) coverage with official MCP01:2025-MCP10:2025 alignment
• SAO behavioral model (Subject-Action-Object) for systematic agent threat enumeration
• 13 pre-built agent attack chains with MITRE ATT&CK technique sequences
• Trust inversion model formalizing SKILL.MD = UNTRUSTED paradigm for agent security

See [CHANGELOG.md](CHANGELOG.md) for full version history.

What's New in v3.0.2

• Major system architecture refactoring, improved security analysis depth and path coverage
• Backported SM2 state machine from next-gen AI-Native penetration testing system named "Cobweb" for problem-solving in depth
• Added multi-version task history and precise structured phase outputs for CI/CD integration
• Optimized context engineering and data disclosure, ~35% token reduction

See [CHANGELOG.md](CHANGELOG.md) for full version history.

Installation

Option 1: Global Installation (Recommended)

# Clone to global skills directory
git clone https://github.com/fr33d3m0n/threat-modeling.git \
    ~/.claude/skills/threat-modeling

# Enable hooks (optional, for automatic validation)
cp ~/.claude/skills/threat-modeling/hooks/settings-example.json \
   ~/.claude/settings.json

Option 2: Project-Local Installation

# Clone to project's .claude/skills directory
mkdir -p .claude/skills
git clone https://github.com/fr33d3m0n/threat-modeling.git \
    .claude/skills/threat-modeling

Requirements

• Claude Code CLI
• Python 3.10+
• SQLite3 (for knowledge base queries)

Quick Start

...