Lewati ke konten
TakoAPI
Kembali ke skill

clawdefender

oleh nukewire

Clawdbot Tools
7.0kUnduhan dilaporkan oleh clawskills.sh
29Bintang
1Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Security scanner and input sanitizer for AI agents.

Deskripsi

Apa yang Dilakukan Skill Ini

Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal across 90+ patterns. Runs as shell scripts that pipe into any agent workflow.

It runs as a standard shell pipe with no external dependencies, so it integrates into any existing agent workflow without additional configuration.

Kapan Menggunakannya

  • Auditing all installed skills for malware before running them
  • Sanitizing API responses before an agent acts on them
  • Validating a URL before fetching to prevent SSRF
  • Filtering GitHub issue content to block embedded injection attempts
  • Blocking credential theft attempts in untrusted email content

Contoh Alur Kerja

INPUT

User asks: sanitize this API response before the agent processes it

AGENT
  1. 1

    Pipe the API response through sanitize.sh with the --json flag

  2. 2

    Scanner checks content against prompt injection, command injection, and exfiltration patterns

  3. 3

    Flagged sections are wrapped with warning markers and withheld from processing

  4. 4

    Clean content passes through for normal agent use

OUTPUT

Sanitized JSON ready for the agent, with suspicious sections marked and flagged to the user

Instalasi

clawhub install nukewire/clawdefender

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

Tautan