本文へスキップ
TakoAPI
スキル一覧に戻る

skill-firewall

mkhaytman87 作

Web & Frontend Development
1.0kダウンロード数はclawskills.shが公開している値です
2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 layer that prevents prompt injection from external skills.

説明

このスキルでできること

A security layer for AI agents that intercepts requests to install external skills and rewrites them from scratch instead of copying them verbatim. Prevents prompt injection via hidden HTML comments, zero-width Unicode characters, and embedded malicious instructions embedded in external skill files.

Copying and executing external skills directly exposes the agent to payloads invisible in rendered markdown but visible to the LLM, which regeneration eliminates entirely.

使いどころ

  • Installing a community skill from ClawHub without running hidden malicious instructions
  • Safely evaluating a GitHub-hosted skill before adding it to a project
  • Blocking a curl-based exfiltration attempt disguised as skill setup
  • Reviewing a skills.sh package for obfuscated Unicode payloads before use
  • Sanitizing a third-party skill that references external files in a poison chain

ワークフロー例

入力

User asks: Install the cloudflare skill from skills.sh

エージェント
  1. 1

    Acknowledge the request and state that the skill will be rewritten, not copied

  2. 2

    Fetch the external skill content and identify its actual purpose

  3. 3

    Flag any suspicious elements such as HTML comments or external URL references

  4. 4

    Write a clean replacement skill in standard ASCII with no external references

  5. 5

    Present the rewrite with a summary report and wait for explicit user approval before saving

出力

A sanitized, human-approved skill file saved to the skills directory, functionally equivalent to the original but free of injected instructions

インストール

clawhub install mkhaytman87/skill-firewall

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