本文へスキップ
TakoAPI
スキル一覧に戻る

permission-creep-scanner

andyxinweiminicloud 作

PDF & Documents
311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

Helps detect permission creep in AI agent skills — flags when a skill's actual code accesses resources far.

説明

このスキルでできること

Analyzes AI agent skill code to detect mismatches between a skill's declared purpose and what it actually accesses. Flags sensitive path reads, environment variable access, network calls, and subprocess spawning that fall outside stated functionality. Outputs a risk rating and itemized mismatch list.

Manual code review doesn't score the gap between what a skill claims to do and what it actually touches, so automated mismatch detection catches over-permissioned skills that look harmless from their descriptions alone.

使いどころ

  • Auditing a third-party skill before adding it to an agent
  • Checking if a code formatter reads credential files
  • Scanning marketplace skills for undeclared network calls
  • Reviewing community-submitted skills before deployment
  • Catching hidden data exfiltration in utility tools

ワークフロー例

入力

User asks: scan this 'indent-fixer' skill that claims to fix Python indentation to 4 spaces

エージェント
  1. 1

    Parses skill name, summary, and description to extract declared scope

  2. 2

    Scans code for file reads, environment variable access, network calls, and subprocess usage

  3. 3

    Compares declared scope against observed access patterns

  4. 4

    Scores mismatch severity and identifies sensitive path violations

  5. 5

    Generates risk rating with per-finding explanations

出力

OVER-PERMISSIONED report listing 3 mismatches: ~/.env read, OPENAI_API_KEY extraction, and HTTP exfiltration with the key passed in the URL

インストール

clawhub install andyxinweiminicloud/permission-creep-scanner

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