本文へスキップ
TakoAPI
スキル一覧に戻る

pincer

panzacoder 作

AI & LLMs
1.1k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

Security-first wrapper for installing agent skills.

説明

このスキルでできること

A security wrapper for clawhub install that scans agent skills before they're installed. Checks for prompt injection, malware payloads, obfuscated commands, and bundled binaries using mcp-scan and its own pattern detection. Blocks or flags dangerous skills based on configurable risk thresholds and publisher reputation.

Unlike running clawhub install directly, pincer applies multi-layer scanning (mcp-scan, shell pattern matching, binary detection, and publisher reputation checks) before any code lands on your machine.

使いどころ

  • Installing a ClawHub skill without manually reviewing its source code
  • Auditing all currently installed skills after a public security advisory
  • Blocking a suspicious publisher from being installed in the future
  • Scanning a locally developed skill before distributing it
  • Reviewing installation history to see what skills an agent environment has run

ワークフロー例

入力

User asks: install the 'bird' skill safely

エージェント
  1. 1

    Fetches the skill from ClawHub and checks publisher trust status

  2. 2

    Runs mcp-scan to detect prompt injection and malware payloads

  3. 3

    Checks for suspicious shell patterns like curl piped to sh or xattr quarantine removal

  4. 4

    Scans for bundled executables (Mach-O, ELF, PE32 binaries)

  5. 5

    Assesses overall risk level and installs if clean, or blocks and reports findings

出力

Skill installed after passing all security checks, or blocked with a detailed risk report listing each detected issue

要件

  • clawhub CLI installed
  • uv installed (provides uvx, required for mcp-scan)

インストール

clawhub install panzacoder/pincer

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