security-hooks

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Security

Grade A, and why

security-hooks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

plugins/security-hooks/.claude-plugin/plugin.json · 33 lines

What it actually says

{
  "name": "security-hooks",
  "description": "MCP security scanner and protected branch hooks for Claude Code",
  "version": "1.1.0",
  "author": {
    "name": "Richard Claydon"
  },
  "license": "MPL-2.0",
  "keywords": ["security", "hooks", "mcp", "branch-protection"],
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "mcp__.*",
        "hooks": [
          {
            "type": "command",
            "command": "\"${CLAUDE_PLUGIN_ROOT}\"/hooks/mcp-security-scanner.sh"
          }
        ]
      },
      {
        "matcher": "^(Edit|Write|Bash|Task)$",
        "hooks": [
          {
            "type": "command",
            "command": "\"${CLAUDE_PLUGIN_ROOT}\"/hooks/protect-main-branch.sh"
          }
        ]
      }
    ]
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

Related

Other plugins, from other repositories