HomeProjectsArticlesPK BoardAbout
Explore Projects

Anthropic Cybersecurity Skills

Active
GitHub Python Apache-2.0

Description

754 structured cybersecurity skills for AI agents mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND and NIST AI RMF. Works with Claude Code, Codex CLI, Cursor, Gemini CLI and 20+ platforms.

Key Features

  • 754 structured cybersecurity skills spanning 26 security domains in agentskills.io format
  • Unified cross-framework mapping to MITRE ATT&CK v19.1, NIST CSF 2.0, MITRE ATLAS, D3FEND, and NIST AI RMF
  • Compatible with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI and 20+ AI platforms
  • YAML frontmatter for sub-second discovery with structured Markdown for step-by-step execution
  • Covers 15 MITRE ATT&CK tactics with 286 techniques including ICS and Mobile
  • Production-grade skill definitions with prerequisites, execution steps, and verification methods

Use Cases

💡 Equipping AI security agents with expert-level threat hunting and DFIR playbooks
💡 Mapping organizational security posture to NIST CSF 2.0 and MITRE ATT&CK frameworks
💡 Training penetration testing workflows with structured adversary TTPs
💡 Building compliant AI risk management with MITRE ATLAS and NIST AI RMF mappings

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (32.0k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Responsive to issues, low backlog

Tags

python security agent tools testing

Categories

🛡️ Security & Guardrails

Quick Start

npx skills add mukul975/Anthropic-Cybersecurity-Skills
Visit GitHub

Related Projects

OpenShell

8.5k · Rust
Active A

OpenShell is the safe, private runtime for autonomous AI agents, developed by NVIDIA. Provides controlled execution environments and resource management.

rustagentframework +2
  • · Sandboxed execution environments protecting data, credentials, and infrastructure with declarative YAML policies
  • · Four defense-in-depth layers: filesystem, network, process, and inference policy enforcement
  • · Hot-reloadable network and inference policies via `openshell policy set` without restarting sandboxes
View full details → View on GitHub

DeepCamera

3.0k · JavaScript
Normal A

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. LLM-powered agentic security camera agent with pluggable AI skills. Runs on Mac Mini & AI PC.

javascriptagenttools +3
  • · VLM scene analysis and object detection running locally with Qwen, DeepSeek, SmolVLM
  • · 19+ pluggable AI skills across detection, segmentation, annotation, and training
  • · Auto-detection of GPU/NPU/CPU hardware with TensorRT, CoreML, OpenVINO acceleration
View on GitHub

AgentGateway

4.7k · Rust
Active A

Next generation agentic proxy for AI agents and MCP servers. Provides unified traffic management, routing, and security control.

rustmcpagent +3
  • · Unified LLM gateway with OpenAI-compatible API routing to OpenAI, Anthropic, Gemini, Bedrock and more
  • · MCP gateway with tool federation, stdio/HTTP/SSE transports, OpenAPI integration and OAuth authentication
  • · A2A gateway enabling secure agent-to-agent communication with capability discovery and task collaboration
View on GitHub

PyRIT

4.4k · Python
Active A

The Python Risk Identification Tool for generative AI — an open-source framework by Microsoft for proactively identifying risks in generative AI systems through red teaming and automated probing.

pythonsecurityevaluation +2
  • · Automated red teaming framework: automated attack probing tool designed specifically for generative AI systems, helping security professionals systematically identify security risks in LLM applications
  • · Multi-stage attack strategies: supports progressive attack paths from simple prompt injection to complex multi-turn dialogues, simulating adversarial behavior in real threat scenarios
  • · Risk quantification and scoring: built-in metrics like Attack Success Rate (ASR) for quantifying system security risks, supporting comparison of different protection strategy effectiveness
View on GitHub