本文へスキップ
TakoAPI
スキル一覧に戻る

agents-skill-security-audit

cerbug45 作

CLI Utilities
683ダウンロード数はclawskills.shが公開している値です
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

Minimal helper to audit skill.md-style instructions for supply-chain risks.

説明

このスキルでできること

Scans skill.md-style instruction files for supply-chain risks using heuristic pattern matching. It flags exfiltration patterns such as HTTP POST requests, curl calls to unknown domains, reads of sensitive files like ~/.env, and credential keywords. Output is a markdown report with a risk level.

It targets the specific structure of skill.md instruction files rather than running generic secrets scanning, so it catches context-aware patterns like credential reads embedded in agent prompts.

使いどころ

  • Checking a third-party skill file before installing it
  • Auditing new agent instructions added to a shared team repo
  • Scanning downloaded SKILL.md files before running them locally
  • Adding a skill file check to a CI pipeline before merging
  • Spot-checking an AI agent prompt file for credential leaks

ワークフロー例

入力

User asks: audit this skill.md for supply-chain risks

エージェント
  1. 1

    Receives the path to the skill.md file

  2. 2

    Runs audit.py against the file using heuristic pattern matching

  3. 3

    Scans for HTTP POST calls, curl to unknown domains, ~/.env reads, and credential keywords

  4. 4

    Builds a permission manifest listing filesystem and network touches found

  5. 5

    Outputs a markdown summary with an overall risk level

出力

Markdown report listing flagged patterns and an overall risk level rating

インストール

clawhub install cerbug45/agents-skill-security-audit

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