İçeriğe geç
TakoAPI
Becerilere dön

crabukit

tnbradley tarafından

Coding Agents & IDEs
387İndirme sayıları clawskills.sh tarafından bildirilir
2Yıldızlar
0Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

Security scanner for OpenClaw skills with Clawdex integration.

Açıklama

Bu Beceri Ne Yapar

Static analysis tool that scans OpenClaw skill files for hardcoded secrets, shell injection, dangerous permissions, and malicious code patterns. Assigns a 0-100 risk score to guide install decisions. Integrates with Clawdex to check skills against a database of known-malicious entries.

Combines static behavior analysis with Clawdex's database of 824+ known-bad skills, covering both zero-day detection and signature-based matching in a single scan.

Ne Zaman Kullanılır

  • Scanning a third-party skill before installing it
  • Checking your own skill for leaked secrets before publishing
  • Running automated skill security checks in a CI/CD pipeline
  • Auditing all installed skills after a suspicious incident
  • Getting a risk score breakdown for a skill shared within a team

Örnek İş Akışı

GİRİŞ

User asks: scan ./suspicious-skill/ and tell me if it is safe to install

AJAN
  1. 1

    Run crabukit scan ./suspicious-skill/ in the terminal

  2. 2

    Crabukit queries the Clawdex database for known-malicious matches

  3. 3

    Static analysis inspects SKILL.md and scripts for secrets, eval/exec calls, shell risks, and dangerous permission requests

  4. 4

    Aggregates all findings into a risk score from 0 to 100

  5. 5

    Reports flagged issues by category with severity levels

ÇIKIŞ

Risk score (e.g., 32/100 - High) with a list of specific findings such as a hardcoded API key on line 14 and an unquoted shell variable in install.sh

Kurulum

clawhub install tnbradley/crabukit

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar