Lewati ke konten
TakoAPI
Kembali ke skill

giraffe-guard

oleh lida408

Coding Agents & IDEs
483Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Scan OpenClaw skill directories for supply chain attacks and malicious code.

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

INPUT

User asks: scan the skills directory and give me a JSON report

AGENT
  1. 1

    Run audit.sh with --json flag pointing to the target skills directory

  2. 2

    Scanner applies all 22 detection rules across each skill's files

  3. 3

    Context-aware engine filters out rule mentions inside documentation

  4. 4

    Assigns severity levels (critical/warning) to each finding

  5. 5

    Writes JSON report with matched lines, rule IDs, and file paths

OUTPUT

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

Instalasi

clawhub install lida408/giraffe-guard

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan