Github: https://github.com/fatehMohamed14/anthropic-cybersecurity-skills-defensive, This is a fork from https://github.com/mukul975/anthropic-cybersecurity-skills.
The original repository is great. It includes 818 skills all together: detection playbooks next to live exploit code, credential crackers and C2 framework guides. Very useful for teams. Dangerous for others. Here is what is different:
🚫 𝟏𝟎𝟔 offensive skills removed - every exploit every C2 framework, every credential-cracking tool. 712 Skills that are purely defensive are left.
🔒 Safe by design - nothing in the skill path can run an attack. Use it for learning for authorized testing or right alongside production systems.
🧰 Per-skill tool manifest added - a machine- list of exactly which tool (Splunk, VirusTotal, Volatility, YARA…) each skill actually needs, so you know what to install before you try to run it.
📋 Curated, documented not just asserted - the removal criteria and the full list of what was cut are public in the repo so the "defensive-only" claim is auditable not just a README promise.
🔌 Bundled MCP servers - to-connect MCP servers, for [name the actual ones - e.g. VirusTotal, DNS/WHOIS lookups] so skills can call real tools out of the box instead of just describing them.
Top comments (0)