本文へスキップ
TakoAPI
スキル一覧に戻る

clawdefender

nukewire 作

Clawdbot Tools
7.0kダウンロード数はclawskills.shが公開している値です
29スター
1閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Security scanner and input sanitizer for AI agents.

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

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

エージェント
  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

出力

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

インストール

clawhub install nukewire/clawdefender

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク