giraffe-guard
由 lida408 提供
Coding Agents & IDEs简介
Scan OpenClaw skill directories for supply chain attacks and malicious code.
描述
该技能的功能
Scans OpenClaw skill directories for supply chain attacks and malicious code using 22 detection rules. Context-aware analysis distinguishes documentation from executable code to reduce false positives. Outputs colored terminal results or JSON reports.
Zero external dependencies means it runs on any macOS or Linux system without setup, unlike scanners that require language runtimes or package installs.
何时使用
- Auditing a new third-party skill before installing it
- Running automated security checks in a CI pipeline for skill repos
- Identifying prompt injection attempts hidden in SKILL.md files
- Detecting typosquatted npm/pip packages bundled with skills
- Finding reverse shells or credential exfiltration patterns in skill scripts
示例工作流
User asks: scan the skills directory and give me a JSON report
- 1
Run audit.sh with --json flag pointing to the target skills directory
- 2
Scanner applies all 22 detection rules across each skill's files
- 3
Context-aware engine filters out rule mentions inside documentation
- 4
Assigns severity levels (critical/warning) to each finding
- 5
Writes JSON report with matched lines, rule IDs, and file paths
JSON report listing all critical and warning findings with file locations, matched content, and rule identifiers, plus exit code 2 if critical issues were found
安装
clawhub install lida408/giraffe-guard运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。