vnmoorthy

Immune — Security skill for Claude Code

Security community

Immune — the agent security loop that turns every attack into an antibody.

How to install Immune

This entry records only its repository, not the path inside it, so there is no exact command to give. Open vnmoorthy/immune and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Immune does

Immune — the agent security loop that turns every attack into an antibody. MCP firewall → replayable breach trace in ClickHouse → synthesized countermeasure → replay-proven → Semgrep rescan → signed receipt → ruling → the next agent is immune. Built at the Cyberdefense Hackathon, SF Tech Week 2026.

Alternatives in Security

Skill Coverage Audit — Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs 2.8k ★
Unifly Audit — Security audit of UniFi configuration 248 ★
Raptor Loop Hunt — RAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill 212 ★

README

Immune — every attack becomes an antibody

Immune

The agent security loop that turns every attack into an antibody.
An MCP firewall catches the attack. A remediator synthesizes the countermeasure, proves it by replaying the whole corpus in ClickHouse,
signs a receipt, publishes a ruling — and the identical attack bounces off the next agent, with a citation.

Website · Run it · The loop · Generalization · Architecture · Use it with Claude Code · Demo script · Demo video · Deck