agentrigs
+ submit rig
~ / rigs / ryo-ebata / cc-audit

ryo-ebata/cc-audit

AI-free static security scanner for Claude Code artifacts (Skills, Hooks, MCP configs). Detects data exfiltration, prompt injection, and supply chain risks with deterministic, reproducible results.

↗ GitHub ★ 25 MIT updated 1d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.7k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit ryo-ebata/cc-audit/.claude ./rig-cc-audit  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit ryo-ebata/cc-audit/.claude/skills/cli-architecture .claude/skills/cli-architecture
$ npx degit ryo-ebata/cc-audit/.claude/skills/rust-best-practices .claude/skills/rust-best-practices
$ npx degit ryo-ebata/cc-audit/.claude/skills/tdd-coach .claude/skills/tdd-coach
$ curl -fsSL --create-dirs -o .claude/agents/dangerous-agent.md https://raw.githubusercontent.com/ryo-ebata/cc-audit/main/examples/subagent/.claude/agents/dangerous-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/safe-agent.md https://raw.githubusercontent.com/ryo-ebata/cc-audit/main/examples/subagent/.claude/agents/safe-agent.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
cc-audit local / custom 2.5k

Skills (3)

cli-architecturerust-best-practicestdd-coach

Subagents (2)

dangerous-agentAn agent with security issues for testing
safe-agentA safe agent with minimal permissions

Slash commands (3)

/fix-ci/dangerous-deploy/safe-build

Similar rigs

JSK9999/ai-nexus
AI coding assistant rule manager for Claude Code, Cursor, and Codex. Load only the rules you need.
★ 10 project Claude CodeCodex 17 skills 7mo ago
Skill Collector 958 tok ·
koolamusic/claudefiles
A minimal catalog of my favourite skills for working with claude
★ 130 project Claude Code 23 skills 6 hooks 1d ago
Skill Collector 4.6k tok ·
ragnarwestad/aide
Spec-driven development for AI coding assistants (Claude Code, Codex, OpenCode, Copilot) — specs, skills and a dashboard that runs them.
★ 1 project Claude CodeCodex 25 skills today
Skill Collector 6.6k tok ·
dirien/yet-another-agent-harness
A Go agent harness for Claude Code — runtime hooks, MCP server, session tracking, middleware chains, and full config generation in one binary
★ 20 setup Claude CodeCodexGemini CLI 3 mcp 50 skills 12 agents 5 hooks 4mo ago
Orchestrator 15.9k tok ·
copied ✓