ClawScan 是一种可组合的安全扫描工具，用于特工技能。

运行一套技能安全扫描仪，将结果传递给裁判工具，并与多个技能安全基准进行比较。

快速启动

安装ClawScan：

macOS 二进制文件支持 macOS 13 或更高版本的 Apple Silicon 和 Intel 版本。CI 使用 苹果硅xcode-27运行程序，并验证Rosetta下的x86_64二进制。 发布和 npm 构建钉住 macOS 13 部署目标，并检查两个二进制文件的最低操作系统元数据。 源代码构建需要Go 1.27.1或更高版本;模块选择已补丁的Go 1.27.3构建工具链。

命令支持的扫描器和裁判默认运行在 ClawScan 的 Docker 运行时， 所以保持 Docker 运行以便本地扫描。

对本地 skills/ 文件夹运行 NVIDIA SkillSpector 和 Cisco Skill Scanner：

扫描已知恶意技能

这个例子扫描了 Trail of Bits 的 csv-summarizer 技能，它声称能总结 CSV 文件，但运行时也会打印所有环境变量。

样本发现：

结果包保留了顶层的产物和每个扫描仪的 JSON 报告。

文物摘录

动机

ClawScan 📡

ClawScan is a composable security scanning harness for agent skills.

Run a suite of skill security scanners, pass the results to a judge harness, and compare against multiple skill security benchmarks.

Quick Start

Install ClawScan:

npm install -g @openclaw/clawscan

The macOS binaries support macOS 13 or later on Apple Silicon and Intel. CI uses the Apple Silicon xcode-27 runner and verifies x86_64 binaries under Rosetta. Release and npm builds pin the macOS 13 deployment target and check both binaries’ minimum OS metadata. Source builds require Go 1.27.1 or later; the module selects the patched Go 1.27.3 build toolchain.

Command-backed scanners and judges run in ClawScan’s Docker runtime by default, so keep Docker running for local scans.

Run NVIDIA SkillSpector and Cisco Skill Scanner against a local skills/ folder:

clawscan --scanner skillspector --scanner cisco

Scan a known malicious skill

This example scans Trail of Bits’ csv-summarizer skill, which claims to summarize a CSV file but also prints every environment variable when run.

git clone https://github.com/trailofbits/overtly-malicious-skills.git /tmp/overtly-malicious-skills
cd /tmp/overtly-malicious-skills
git checkout 4ffbf9461ef0505f9ce76a0d3694a18ec33ea531
clawscan skills/csv-summarizer \
  --scanner skillspector \
  --scanner cisco \
  --output /tmp/clawscan-csv-summarizer.json

Sample findings:

targets: 1
scanner_completed: 2
scanner_failed: 0
scanner_skipped: 0
issues_found: 2
gate: pass
errors: 0
full_results: /tmp/clawscan-csv-summarizer.json

The results bundle keeps the top-level artifact plus per-scanner JSON reports.

{
  "schemaVersion": "clawscan-run-v1",
  "target": "skills/csv-summarizer",
  "scanners": {
    "cisco": {
      "status": "completed",
      "durationMs": 42,
      "outputPath": "clawscan-csv-summarizer/skills/csv-summarizer/cisco.json",
      "isSafe": true,
      "maxSeverity": "SAFE",
      "findingsCount": 0
    },
    "skillspector": {
      "status": "completed",
      "durationMs": 42,
      "outputPath": "clawscan-csv-summarizer/skills/csv-summarizer/skillspector.json",
      "severity": "MEDIUM",
      "score": 31,
      "recommendation": "CAUTION",
      "issues": [
        {
          "id": "LP3",
          "severity": "MEDIUM",