本文へスキップ
TakoAPI
スキル一覧に戻る

agent-hardening

x1xhlol 作

CLI Utilities
649ダウンロード数はclawskills.shが公開している値です
4スター
0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

Test your agent's input sanitization against common injection attacks.

説明

このスキルでできること

Runs self-contained security checks on OpenClaw agents to test input sanitization. Covers unicode control character stripping, HTML comment injection detection, and bidi override character identification. Uses only hardcoded synthetic samples — no local files or external connections.

Requires nothing beyond Python 3, so checks run immediately with no setup, accounts, or network access.

使いどころ

  • Verify an agent strips zero-width unicode characters before processing user input
  • Detect hidden HTML directives injected into agent context windows
  • Check if filename spoofing via bidi override characters is caught
  • Run a quick pre-deployment security audit on a new agent
  • Validate input sanitization logic during agent development

ワークフロー例

入力

User asks: run the agent hardening checks on my agent

エージェント
  1. 1

    Runs unicode control character sanitization test against synthetic samples

  2. 2

    Runs HTML comment injection detection against sample strings

  3. 3

    Runs bidi override detection against sample filenames

  4. 4

    Reports pass/fail counts for each check category

出力

Summary showing how many checks passed per category, with flagged samples highlighted

インストール

clawhub install x1xhlol/agent-hardening

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