跳到正文
TakoAPI
返回技能列表

capability-graph-mapper

由 andyxinweiminicloud 提供

Git & GitHub
359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 map the composite permission surface across AI agent skill dependency chains.

描述

该技能的功能

Maps the composite permission surface across an agent's installed skill set. Traces what each skill can do individually, then computes what combinations enable — surfacing emergent risks like credential exfiltration paths that no single skill declares on its own.

Standard dependency auditors check known CVEs in individual packages but don't model how combined tool permissions create new attack surfaces in agent systems.

何时使用

  • Auditing a new agent build before deploying to production
  • Evaluating a third-party skill before adding it to an existing agent
  • Finding credential exfiltration paths across a multi-skill setup
  • Generating a risk report for an agent security review
  • Checking how much the attack surface shrinks after removing a skill

示例工作流

输入

User asks: Map the capability surface for an agent with skills: log-analyzer, http-poster, env-reader, markdown-formatter

智能体
  1. 1

    Extract declared capabilities for each skill (file access, network, shell execution, env reads)

  2. 2

    Build a permission matrix mapping each skill to its capability flags

  3. 3

    Check all pairwise and transitive combinations against known dangerous patterns

  4. 4

    Compute a privilege surface score (0-100) for the full skill set

  5. 5

    Output flagged emergent risks with severity ratings and recommendations

输出

A capability graph report with a permission matrix, 3 flagged risks including HIGH-severity env-reader to http-poster credential exfiltration and a three-hop obfuscation chain, a privilege surface score of 67/100, and targeted recommendations for which skill combinations to review or sandbox

安装

clawhub install andyxinweiminicloud/capability-graph-mapper

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