← 返回 Skills 市场
738
总下载
3
收藏
7
当前安装
1
版本数
在 OpenClaw 中安装
/install reverse-engineering
功能描述
Reverse engineer binaries, APIs, protocols, and workflows with evidence ladders, interface maps, and falsifiable hypotheses.
安全使用建议
This skill appears coherent and reasonable. Before installing, confirm you are comfortable with the agent creating a ~/reverse-engineering/ workspace and storing notes there, and never provide credentials or access to production systems unless you explicitly authorize a specific, narrowly scoped, safe step. Remember reverse engineering can be dual‑use—only use this on targets you are authorized to analyze and keep sensitive samples local unless you explicitly approve sharing them.
功能分析
Type: OpenClaw Skill
Name: reverse-engineering
Version: 1.0.0
The 'reverse-engineering' skill bundle is a well-structured framework designed to guide an AI agent through forensic analysis of binaries, APIs, and protocols. It emphasizes a rigorous methodology (the TRACE protocol in protocol.md) and an evidence-based confidence model (evidence-ladder.md). Critically, the bundle includes strong safety guardrails in boundaries.md and SKILL.md, explicitly instructing the agent to prioritize authorized access, prefer offline copies, and avoid invasive actions or credential theft. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
Name and description match the actual contents: a structured reverse‑engineering method, templates, and guidance. Requested resources (a local workspace ~/reverse-engineering/) are proportional to the purpose.
Instruction Scope
SKILL.md and supporting files prescribe read-only-first rules, explicit user approval before invasive or credential-bearing steps, and local-only storage by default. There are no instructions to read unrelated system files, contact external endpoints, or exfiltrate data.
Install Mechanism
No install spec or code files that would write or execute code on disk; this is instruction-only, which minimizes risk and is appropriate for the stated purpose.
Credentials
The skill declares no required environment variables, binaries, or credentials. The only persistent artifact is an optional local workspace (~/reverse-engineering/) which the skill explicitly asks permission to create and populate.
Persistence & Privilege
The skill stores durable notes and session files in a single user-controlled directory and requires confirmation before the first persistent write. always is false and there is no attempt to modify other skills or global agent settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install reverse-engineering - 安装完成后，直接呼叫该 Skill 的名称或使用
/reverse-engineering触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Adds a structured reverse engineering workflow with evidence tracking, interface mapping, and safer uncertainty handling.
元数据
常见问题
Reverse Engineering 是什么？
Reverse engineer binaries, APIs, protocols, and workflows with evidence ladders, interface maps, and falsifiable hypotheses. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 738 次。
如何安装 Reverse Engineering？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install reverse-engineering」即可一键安装，无需额外配置。
Reverse Engineering 是免费的吗？
是的，Reverse Engineering 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Reverse Engineering 支持哪些平台？
Reverse Engineering 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 Reverse Engineering？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills