跳到正文
TakoAPI
返回技能列表

permission-creep-scanner

由 andyxinweiminicloud 提供

PDF & Documents
311下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

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

描述

该技能的功能

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.

何时使用

  • 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

示例工作流

输入

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

智能体
  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

输出

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

安装

clawhub install andyxinweiminicloud/permission-creep-scanner

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接