Skip to main content

roe-template

Rules of Engagement document creation — scope definition, prohibited/permitted actions, testing windows, escalation contacts, incident procedures.

跳到安装

来源信息

仓库
BitterSecurity/Decepticon
最近来源活动
2026年6月12日 09:59
检测到的 SKILL.md 语言
英语
星标
5,522
分支
1,048

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

文件资源管理器
3 个文件

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
roe-template
description
Rules of Engagement document creation — scope definition, prohibited/permitted actions, testing windows, escalation contacts, incident procedures.
allowed-tools
Read Write Edit
metadata
{"subdomain":"planning","when_to_use":"create RoE, define scope, engagement boundaries, start new engagement","tags":"roe, scope, engagement, authorization, legal","upstream_ref":"Soundwave Rules of Engagement template — scope / window / escalation / incident procedures"}
# Rules of Engagement (RoE) Generator The RoE is the **legally binding** foundation of every red team engagement. All other documents build on it. ## When to Use - Starting a new engagement - User says "create RoE", "define scope", "set boundaries" - Before any other planning document can be created ## Workflow ### Step 1: Interview the User Drive each dimension through one `ask_user_question` call (per CRITICAL_RULES #8 — every operator-facing question goes through the tool). Cover these roughly in order, never bundling multiple questions in one turn: **Identity & Scope** 1. Engagement name (free-form, `allow_other=true` with sensible guesses) 2. Client organization (free-form, `allow_other=true`) 3. Engagement type — single-select: `external` / `internal` / `hybrid` / `assumed-breach` / `physical` 4. Start date / end date / testing window with timezone (free-form, `allow_other=true` — suggest defaults like "Mon-Fri 09:00-18:00 client TZ") 5. In-scope targets (free-form, `allow_other=true` — domains, IP ranges, cloud resources, applications) 6. Out-of-scope targets (free-form, `allow_other=true`) **Boundaries & Escalation** 7. Additional prohibited actions beyond schema defaults (multi-select with sensible options + `allow_other=true`) 8. Special permitted actions — phishing, password spraying, raw-socket scans (multi-select) 9. Escalation contacts — minimum 2 (client + red team lead). One ask per contact slot covering name, role, channel 10. Authorization reference / contract # (free-form, `allow_other=true`) ### Step 2: Generate plan/roe.json Use the `RoE` schema from `decepticon.core.schemas`. Write to the engagement directory. See `references/roe-example.json` for a complete example and `../references/schema-quick-reference.md` for all required fields and valid values. ### Step 3: Validate Run through the checklist in `references/validation-checklist.md` before presenting to user. ## Generation Rules 1. **Always include default prohibited actions** — DoS, unauthorized social engineering, unauthorized physical access, real data exfiltration, production data modification 2. **Scope must be specific** — CIDR notation for IPs, wildcard notation for domains 3. **Testing window must include timezone** 4. **At least 2 escalation contacts** required 5. **Authorization reference must not be empty** ## Output Write `plan/roe.json` to the engagement directory, then present a human-readable summary to the user for confirmation.
在 GitHub 查看