Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问clear审计未展示

traces-and-audit跟踪和审计

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

931

周安装

40

GitHub Stars

公开资料未说明

下载量

326
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:traces-and-audit(跟踪和审计)
来源仓库:https://github.com/tracemem/tracemem-skills
仓库路径:skills/traces-and-audit
安装命令:
npx skills add tracemem/tracemem-skills --skill "traces-and-audit"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add tracemem/tracemem-skills --skill "traces-and-audit"

简介

用于安全审计、权限检查和常见漏洞排查,增强系统安全性。

  • 适合让 Agent 梳理敏感配置、分析鉴权逻辑或生成复核清单。
  • 通过 npx skills add 命令从 tracemem-skills 仓库安装。
  • 不能将工具输出直接当作最终结论,需人工复核关键结果。
  • 涉及密钥或生产系统时,应先确认最小权限和操作边界。

SKILL.md

name
traces-and-audit
description
Auditing memory traces and debugging.

Skill: TraceMem Traces and Audit

Purpose

This skill explains the concept of the Decision Trace as an artifact. Understanding this helps you write better "evidence" into the system.

When to Use

  • When you need to understand *what* TraceMem is actually recording.
  • When generating reports or answering questions about past actions ("Why did you do that?").

When NOT to Use

  • You generally do not "use" this skill to execute actions, but to inform *how* you execute them.

Core Rules

  • The Trace is the Truth: If it's not in the trace, it didn't happen (legally/audit-wise).
  • Append-Only: You cannot go back and fix history.
  • Complete Picture: A trace includes your ID, the time, the policy version, the data schema version, and the exact outcomes.

Correct Usage Pattern

  1. Design for Readability:

When running a decision, imagine a human reading the trace 6 months later. - "Why did this agent delete this user?" - Look at the intent, look at the context you added, look at the policy result. - If the trace answers the question, you succeeded.

  1. Linking:

If you chain decisions (one decision triggers another workflow), reference the parent decision_id in the child's metadata or context.

Common Mistakes

  • Phantom Actions: Doing side effects (like calling an external API) *without* recording it in TraceMem or via a Data Product. This creates "dark matter" — actions that have no record.
  • Incomplete Evidence: Reading data via a side-channel (not a Data Product) and then acting on it. The trace will show the action but not the data that justified it.

Safety Notes

  • Exoneration: A good trace protects *you* (the agent). If a policy was wrong, the trace proves you followed the policy correctly. If data was bad, the trace proves you acted on the bad data you were given.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenCode

29.98%
按下载量换算98

Antigravity

24.12%
按下载量换算79

Claude Code

19.15%
按下载量换算62

Gemini CLI

11.58%
按下载量换算38

Cursor

7.59%
按下载量换算25

windsurf

3.32%
按下载量换算11

安全审计

暂无安全审计结果可展示。

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills