Menu
使用AgentShield扫描您的Claude代码配置（.claude/目录），以发现安全漏洞、配置错误和注入风险。检查CLAUDE.md、settings.json、MCP服务器、钩子和代理定义。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Serve a model on a completed Itô compute booking through the canonical Itô backend. Use after ito-compute has booked GPU nodes and the user wants an OpenAI-compatible endpoint on that metal. Chains off a booking record; ECC implements no serving stack of its own.
Run an ML training job on a completed Itô compute booking through the canonical Itô backend. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. Chains off a booking record; ECC implements no training stack of its own.
GAN（生成的敵対ネットワーク）スタイルの評価ハーネス、画像生成パターン、および品質メトリクス。
受GAN启发的生成器-评估器代理框架，用于自主构建高质量应用。基于Anthropic 2026年3月的框架设计论文。
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.
Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery modes. Use when Codex needs to open an interactive CLI, SSH session, local development process, sandbox, or other argv-based command in a new host terminal; diagnose whether a supported terminal is available; or provide an actionable plan when the requested terminal is unsupported.
| name | security-scan |
| description | 使用AgentShield扫描您的Claude代码配置（.claude/目录），以发现安全漏洞、配置错误和注入风险。检查CLAUDE.md、settings.json、MCP服务器、钩子和代理定义。 |
| origin | ECC |
使用 AgentShield 审计您的 Claude Code 配置中的安全问题。
.claude/settings.json、CLAUDE.md 或 MCP 配置后| 文件 | 检查项 |
|---|---|
CLAUDE.md | 硬编码的密钥、自动运行指令、提示词注入模式 |
settings.json | 过于宽松的允许列表、缺失的拒绝列表、危险的绕过标志 |
mcp.json | 有风险的 MCP 服务器、硬编码的环境变量密钥、npx 供应链风险 |
hooks/ | 通过 ${file} 插值导致的命令注入、数据泄露、静默错误抑制 |
agents/*.md | 无限制的工具访问、提示词注入攻击面、缺失的模型规格 |
必须安装 AgentShield。检查并在需要时安装：
# Check if installed
npx ecc-agentshield --version
# Install globally (recommended)
npm install -g ecc-agentshield
# Or run directly via npx (no install needed)
npx ecc-agentshield scan .
针对当前项目的 .claude/ 目录运行：
# Scan current project
npx ecc-agentshield scan
# Scan a specific path
npx ecc-agentshield scan --path /path/to/.claude
# Scan with minimum severity filter
npx ecc-agentshield scan --min-severity medium
# Terminal output (default) — colored report with grade
npx ecc-agentshield scan
# JSON — for CI/CD integration
npx ecc-agentshield scan --format json
# Markdown — for documentation
npx ecc-agentshield scan --format markdown
# HTML — self-contained dark-theme report
npx ecc-agentshield scan --format html > security-report.html
自动应用安全的修复（仅修复标记为可自动修复的问题）：
npx ecc-agentshield scan --fix
这将：
运行对抗性的三智能体流程以进行更深入的分析：
# Requires ANTHROPIC_API_KEY
export ANTHROPIC_API_KEY=your-key
npx ecc-agentshield scan --opus --stream
这将运行：
从头开始搭建一个新的安全 .claude/ 配置：
npx ecc-agentshield init
创建：
settings.jsonCLAUDE.mdmcp.json 占位符添加到您的 CI 流水线中：
- uses: affaan-m/agentshield@v1
with:
path: '.'
min-severity: 'medium'
fail-on-findings: true
| 等级 | 分数 | 含义 |
|---|---|---|
| A | 90-100 | 安全配置 |
| B | 75-89 | 轻微问题 |
| C | 60-74 | 需要注意 |
| D | 40-59 | 显著风险 |
| F | 0-39 | 严重漏洞 |
Bash(*)（无限制的 shell 访问）${file} 插值导致的命令注入2>/dev/null、|| true）npx -y 自动安装