pentest

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Pentest

Synthesis skill for authorized offensive-security engagements. Produces scope-gated plans, checklists, and structured findings — never vendored C2, webshells, or autonomous exploit execution.

Scope: Pre-authorized penetration testing methodology and reporting. NOT for unauthorized testing, malware/C2 operations, static pre-deploy audits (security-scanner), or synthetic CTF-only puzzles (ctf-*).

面向授权 offensive-security测试场景的综合技能。可生成受范围管控的测试计划、检查清单和结构化测试结果——绝不提供商用C2、webshell或自动漏洞利用执行功能。

适用范围： 预授权渗透测试方法论及报告。不适用于未授权测试、恶意软件/C2操作、预部署静态审计（security-scanner）或纯CTF合成谜题（ctf-*）场景。

Canonical Vocabulary

标准术语表

Term	Definition
ROE	Rules of Engagement — signed authorization document defining targets, dates, contacts, and prohibited actions
scope gate	Mandatory `scope_check.py` pass before any recon, web, API, or OSINT offensive planning
target	Host, URL, CIDR, or application explicitly listed in the signed ROE
phase	Engagement stage from `scripts/phases.py` — each requires an active scope gate
triage	Route a signal to canonical playbook + optional external skill via `methodology-router.md`
external index	Planning lock `pentest-external-skill-index.json` via manifest + `lookup_external_slug.py`
finding	Structured JSON record of a suspected issue with severity, evidence, and remediation guidance
playbook	Checklist-driven methodology loaded from `references/playbooks/` — planning only
synthesis	Agent-authored plan/checklist/report assembled from references and operator context
external runner	Optional third-party CLI (e.g. Strix) the operator runs manually — this skill does not install or invoke attacks
fail-closed	Deny all offensive planning when scope is missing, expired, or target-out-of-scope

术语	定义
ROE	Rules of Engagement — 经签署的授权文档，定义了测试目标、时间、联系人及禁止操作
scope gate	强制要求的 `scope_check.py` 校验环节，任何侦察、Web、API或OSINT进攻性规划前必须通过该校验
target	ROE文档中明确列出的主机、URL、CIDR或应用程序
phase	来自 `scripts/phases.py` 的测试阶段——每个阶段均需通过有效的scope gate校验
triage	通过 `methodology-router.md` 将需求导向标准操作手册 + 可选外部技能
external index	通过清单文件 + `lookup_external_slug.py` 实现的规划锁 `pentest-external-skill-index.json`
finding	结构化JSON记录，包含疑似问题的严重程度、证据及修复建议
playbook	从 `references/playbooks/` 加载的基于检查清单的方法论——仅用于规划
synthesis	Agent基于参考资料和操作人员上下文生成的计划/检查清单/报告
external runner	操作人员手动运行的可选第三方CLI（如Strix）——本技能不会安装或调用攻击工具
fail-closed	当范围缺失、过期或目标超出范围时，拒绝所有进攻性规划

Tier Boundaries

层级边界

Tier	Skill	When to use	ROE required	Executes attacks
Static audit	security-scanner	Pre-deployment SAST, secrets, deps, compliance heuristics	No	No — read-only code scan
Authorized pentest	pentest (this skill)	Live apps/APIs under signed engagement	Yes	No — planning/checklists only; operator runs approved tools
CTF / lab	ctf-*	Isolated challenge boxes, training flags, synthetic vuln labs	No (lab policy instead)	Only inside designated lab scope

Redirect rules:

"Scan my repo for secrets/CVEs before merge" → security-scanner
"Hack this site without permission" → refuse — no ROE, no planning
"Solve this HTB/CTF box" → ctf-* skills — not production pentest
"We have signed ROE for staging.example.com" → pentest after scope gate

层级	技能	使用场景	是否需要ROE	是否执行攻击
静态审计	security-scanner	预部署SAST、密钥检测、依赖检查、合规性启发式扫描	否	否——仅只读代码扫描
授权渗透测试	pentest（本技能）	已签署测试协议的在线应用/API	是	否——仅提供规划/检查清单；操作人员运行经批准的工具
CTF / 实验室	ctf-*	独立挑战靶机、训练flag、合成漏洞实验室	否（遵循实验室政策）	仅在指定实验室范围内执行

重定向规则：

"合并前扫描我的仓库以查找密钥/CVE" → security-scanner
"未经许可攻击这个网站" → 拒绝——无ROE则不提供规划服务
"解决这个HTB/CTF靶机" → **ctf-***技能——不属于生产环境渗透测试
"我们已签署针对staging.example.com的ROE" → 通过scope gate校验后使用pentest

Scope Gate (Mandatory)

Scope Gate（强制要求）

Before recon, web, api, osint, or any extended phase mode (

network

cloud

mobile

wireless

llm

internal

binary

blockchain

post-exploit

Obtain
```
--target
```
,
```
--roe-file
```
, and the requested
```
--phase
```
from the operator.
Run:

bash

uv run python scripts/scope_check.py \
  --target "<host-or-url>" \
  --roe-file "<path-to-roe.json>" \
  --phase "<mode>"

Parse JSON stdout. If
```
ok
```
is false or exit code is non-zero → stop. Present
```
deny_reason
```
and load
```
references/scope-and-roe.md
```
for remediation.
Record
```
engagement_id
```
,
```
phase
```
, and
```
allowed_phases
```
from the scope result in session notes.
Never proceed to playbooks, external runners, or attack-sounding commands without a passing scope gate in the current session.

Empty or partial scope requests (target without ROE, ROE without target, expired ROE, out-of-scope host) are denied fail-closed.

在执行recon、web、api、osint或任何扩展阶段模式（

network

、

cloud

、

mobile

、

wireless

、

llm

、

internal

、

binary

、

blockchain

、

post-exploit

）之前：

从操作人员处获取
```
--target
```
、
```
--roe-file
```
及请求的
```
--phase
```
参数。
运行以下命令：

bash

uv run python scripts/scope_check.py \
  --target "<host-or-url>" \
  --roe-file "<path-to-roe.json>" \
  --phase "<mode>"

解析JSON标准输出。如果
```
ok
```
为false或退出码非零 → 停止操作。展示
```
deny_reason
```
并加载
```
references/scope-and-roe.md
```
以获取补救方案。
在会话记录中记录范围校验结果中的
```
engagement_id
```
、
```
phase
```
和
```
allowed_phases
```
。
当前会话未通过scope gate校验前，绝不能进入操作手册、外部运行工具或类似攻击的命令环节。

空请求或部分范围请求（仅提供目标未提供ROE、仅提供ROE未提供目标、ROE过期、目标超出范围）将触发闭环拒绝。

Dispatch

调度规则

$ARGUMENTS	Mode	Action
`doctor`	doctor	Run `scripts/doctor.py` — skill asset and policy readiness
`scope <target>`	scope	Run `scripts/scope_check.py` with `--roe-file` , `--target` , and `--phase` ; echo `restricted_phases` when ROE-gated
`triage <signal>`	triage	Load `references/methodology-router.md` ; map signal → playbook + external slug
`recon <target>`	recon	Scope gate → `references/playbooks/recon.md`
`web <target>`	web	Scope gate → `references/playbooks/web.md` (+ injection/auth playbooks as needed)
`api <target>`	api	Scope gate → `references/playbooks/api.md`
`osint <target>`	osint	Scope gate → `references/playbooks/osint.md` (passive only per ROE)
`network <target>`	network	Scope gate → `references/playbooks/network.md`
`cloud <target>`	cloud	Scope gate → `references/playbooks/cloud.md`
`mobile <target>`	mobile	Scope gate → `references/playbooks/mobile.md`
`wireless <target>`	wireless	Scope gate → `references/playbooks/wireless.md` (explicit ROE)
`llm <target>`	llm	Scope gate → `references/playbooks/llm.md`
`internal <target>`	internal	Scope gate → `references/playbooks/internal.md`
`binary <target>`	binary	Scope gate → `references/playbooks/binary.md`
`blockchain <target>`	blockchain	Scope gate → `references/playbooks/blockchain.md`
`post-exploit <target>`	post-exploit	Scope gate → `references/playbooks/post-exploit.md` (explicit ROE only)
`validate`	validate	Run `scripts/check.py` ; verify findings JSON against schema
`report`	report	Aggregate session findings via `scripts/findings_emit.py` patterns
`help` or (empty)	help	Show modes, scope gate, tier boundaries, reference index
Unrecognized	—	Ask for clarification; do not assume authorization

参数	模式	操作
`doctor`	doctor	运行 `scripts/doctor.py` ——检查技能资产及政策就绪状态
`scope <target>`	scope	使用 `--roe-file` 、 `--target` 和 `--phase` 参数运行 `scripts/scope_check.py` ；当受ROE管控时输出 `restricted_phases`
`triage <signal>`	triage	加载 `references/methodology-router.md` ；将需求映射到操作手册 + 外部标识
`recon <target>`	recon	通过scope gate校验 → 加载 `references/playbooks/recon.md`
`web <target>`	web	通过scope gate校验 → 加载 `references/playbooks/web.md` （必要时加载注入/认证操作手册）
`api <target>`	api	通过scope gate校验 → 加载 `references/playbooks/api.md`
`osint <target>`	osint	通过scope gate校验 → 加载 `references/playbooks/osint.md` （仅执行ROE允许的被动操作）
`network <target>`	network	通过scope gate校验 → 加载 `references/playbooks/network.md`
`cloud <target>`	cloud	通过scope gate校验 → 加载 `references/playbooks/cloud.md`
`mobile <target>`	mobile	通过scope gate校验 → 加载 `references/playbooks/mobile.md`
`wireless <target>`	wireless	通过scope gate校验 → 加载 `references/playbooks/wireless.md` （需明确ROE授权）
`llm <target>`	llm	通过scope gate校验 → 加载 `references/playbooks/llm.md`
`internal <target>`	internal	通过scope gate校验 → 加载 `references/playbooks/internal.md`
`binary <target>`	binary	通过scope gate校验 → 加载 `references/playbooks/binary.md`
`blockchain <target>`	blockchain	通过scope gate校验 → 加载 `references/playbooks/blockchain.md`
`post-exploit <target>`	post-exploit	通过scope gate校验 → 加载 `references/playbooks/post-exploit.md` （仅明确ROE授权场景）
`validate`	validate	运行 `scripts/check.py` ；验证测试结果JSON是否符合 schema
`report`	report	通过 `scripts/findings_emit.py` 模式聚合会话测试结果
`help` 或（空）	help	展示模式、scope gate步骤、层级边界及参考索引
未识别参数	—	请求操作人员澄清；不得假设已获得授权

Mode: doctor

模式：doctor

Read-only environment and policy checks. No offensive actions.

Run:

uv run python scripts/doctor.py --format json

When the skill is globally installed, set
```
WAGENTS_REPO_ROOT
```
to the agents clone so
```
repo-root
```
and lock-index checks can resolve
```
planning/research-lock/
```
.
Present checks grouped by
```
ok
```
,
```
warn
```
,
```
fail
```
.
If
```
forbidden-tooling
```
is
```
fail
```
, stop — engagement cannot use this skill until operator removes C2/webshell references from the request.
Load
```
references/external-runners.md
```
only when operator asks about optional CLIs.

只读环境及政策检查。无进攻性操作。

运行：

uv run python scripts/doctor.py --format json

当技能全局安装时，设置
```
WAGENTS_REPO_ROOT
```
为agents克隆目录，以便
```
repo-root
```
和锁索引检查能解析
```
planning/research-lock/
```
。
按
```
ok
```
、
```
warn
```
、
```
fail
```
分组展示检查结果。
如果
```
forbidden-tooling
```
为
```
fail
```
，则停止操作——操作人员移除请求中的C2/webshell引用前，无法使用本技能。
仅当操作人员询问可选CLI时，才加载
```
references/external-runners.md
```
。

Mode: scope

模式：scope

Validate authorization before any other offensive mode.

Require
```
--target
```
,
```
--roe-file
```
, and
```
--phase
```
. If any are missing, run
```
scope_check.py
```
without them to produce the deny JSON and explain required fields.

On pass: summarize

engagement_id

phase

allowed_phases

restricted_phases

expires_at

, and in-scope target match.

On deny: cite
```
deny_reason
```
; do not load playbooks.

在执行任何其他进攻性模式前验证授权状态。

必须提供
```
--target
```
、
```
--roe-file
```
和
```
--phase
```
参数。如果缺少任何参数，运行不带参数的
```
scope_check.py
```
生成拒绝JSON并说明所需字段。

校验通过：汇总

engagement_id

、

phase

、

allowed_phases

、

restricted_phases

、

expires_at

及目标匹配情况。

校验拒绝：引用
```
deny_reason
```
；不加载操作手册。

Mode: triage

模式：triage

Route methodology depth without loading all upstream repos.

Parse signal from
```
$ARGUMENTS
```
(e.g.
```
sqli
```
,
```
xss
```
,
```
kerberos
```
,
```
llm-injection
```
).
Load
```
references/methodology-router.md
```
— resolve canonical slug from dedup table.
Load matching
```
references/playbooks/*.md
```
section (one file at a time).
Surface
```
install_command
```
via
```
scripts/lookup_external_slug.py
```
only when operator requests deeper upstream body.
Quarantine: EXT-084 entries are inspect-only — never auto-install.

无需加载所有上游仓库即可确定方法论深度。

解析
```
$ARGUMENTS
```
中的需求信号（如
```
sqli
```
、
```
xss
```
、
```
kerberos
```
、
```
llm-injection
```
）。
加载
```
references/methodology-router.md
```
——从去重表中解析标准标识。
加载匹配的
```
references/playbooks/*.md
```
章节（一次加载一个文件）。
仅当操作人员请求更深入的上游内容时，才通过
```
scripts/lookup_external_slug.py
```
展示
```
install_command
```
。
隔离规则： EXT-084条目仅可查看——绝不自动安装。

Mode: recon

模式：recon

Post-authorization attack-surface planning only.

Pass scope gate (see Scope Gate).
Confirm
```
recon
```
is in
```
allowed_phases
```
from scope result.

Load

references/playbooks/recon.md

(and

references/osint.md

when passive).

Produce a phased plan: asset inventory hypotheses, DNS/WHOIS/certificate angles, technology fingerprinting commands the operator may run — do not run them from this skill's scripts.
Emit planned checkpoints as draft findings only after operator supplies evidence.

仅用于授权后的攻击面规划。

通过scope gate校验（参见Scope Gate章节）。
确认
```
recon
```
在范围校验结果的
```
allowed_phases
```
中。

加载

references/playbooks/recon.md

（被动场景下同时加载

references/osint.md

）。

生成分阶段计划：资产清单假设、DNS/WHOIS/证书分析方向、技术指纹识别操作人员可运行的命令——本技能脚本不会执行这些命令。
仅当操作人员提供证据后，才将计划中的检查点作为草稿测试结果输出。

Mode: web

模式：web

Web application testing planning only.

Pass scope gate; confirm
```
web
```
in
```
allowed_phases
```
.
Load
```
references/playbooks/web.md
```
one section at a time.
Build a prioritized test checklist mapped to OWASP categories — no exploit payloads executed by skill scripts.
For each confirmed issue the operator reports, emit via
```
findings_emit.py
```
(pass
```
--scope-json
```
from the current scope gate result when binding findings to engagement).

仅用于Web应用测试规划。

通过scope gate校验；确认
```
web
```
在
```
allowed_phases
```
中。
分章节加载
```
references/playbooks/web.md
```
。
构建与OWASP类别映射的优先级测试检查清单——技能脚本不会执行任何漏洞利用 payload。
对于操作人员报告的每个已确认问题，通过
```
findings_emit.py
```
输出（绑定测试结果到测试任务时，传入当前scope gate校验结果的
```
--scope-json
```
参数）。

Mode: api

模式：api

API security testing planning only.

Pass scope gate; confirm
```
api
```
in
```
allowed_phases
```
.
Load
```
references/playbooks/api.md
```
.
Produce authn/authz, input validation, rate-limit, and BOLA test matrices.
Reference OpenAPI/GraphQL discovery steps for the operator; never call live targets from bundled scripts.

仅用于API安全测试规划。

通过scope gate校验；确认
```
api
```
在
```
allowed_phases
```
中。
加载
```
references/playbooks/api.md
```
。
生成认证/授权、输入验证、速率限制及BOLA测试矩阵。
为操作人员提供OpenAPI/GraphQL发现步骤参考；捆绑脚本绝不会调用在线目标。

Mode: osint

模式：osint

Passive open-source intelligence planning only.

Pass scope gate; confirm
```
osint
```
in
```
allowed_phases
```
.
Load
```
references/osint.md
```
.
Stay within ROE
```
prohibited_actions
```
— no social engineering, harassment, or out-of-scope third-party data collection.
Output source list, query templates, and verification steps for the operator.

仅用于被动开源情报规划。

通过scope gate校验；确认
```
osint
```
在
```
allowed_phases
```
中。
加载
```
references/osint.md
```
。
严格遵守ROE中的
```
prohibited_actions
```
——不得进行社会工程、骚扰或超出范围的第三方数据收集。
为操作人员输出数据源列表、查询模板及验证步骤。

Mode: post-exploit

模式：post-exploit

Post-exploitation planning only when ROE explicitly allows it.

Pass scope gate; confirm
```
post-exploit
```
in
```
allowed_phases
```
(see
```
restricted_phases
```
in scope JSON).
Load
```
references/playbooks/post-exploit.md
```
.
Produce containment-aware persistence/lateral-movement planning matrices — no C2 install commands, implants, or live exploitation from bundled scripts.
Refuse C2/Havoc/Sliver/Cobalt Strike skill installs; document-only upstream references only.

仅在ROE明确允许时用于后渗透规划。

通过scope gate校验；确认
```
post-exploit
```
在
```
allowed_phases
```
中（参见范围JSON中的
```
restricted_phases
```
）。
加载
```
references/playbooks/post-exploit.md
```
。
生成包含遏制策略的持久化/横向移动规划矩阵——捆绑脚本不会提供C2安装命令、植入程序或在线漏洞利用功能。
拒绝C2/Havoc/Sliver/Cobalt Strike技能安装请求；仅提供文档化的上游参考。

Mode: validate

模式：validate

Deterministic skill and findings validation.

Run:
```
uv run python scripts/check.py
```
If validating ad-hoc findings JSON, compare against
```
references/findings-schema.md
```
.
Report validation status; do not mutate ROE or targets.

确定性技能及测试结果验证。

运行：
```
uv run python scripts/check.py
```
如果验证临时测试结果JSON，将其与
```
references/findings-schema.md
```
进行对比。
报告验证状态；不得修改ROE或目标。

Mode: report

模式：report

Session report synthesis.

Collect findings emitted during the engagement (JSON lines or array).
Validate each record against
```
references/findings-schema.md
```
.
Group by severity; include scope metadata (
```
engagement_id
```
,
```
target
```
, ROE hash).
Use
```
scripts/findings_emit.py --aggregate
```
when normalizing operator-supplied notes.
Executive summary must state authorization basis and prohibited actions respected.

会话报告整合。

收集测试过程中输出的测试结果（JSON行或数组）。
验证每条记录是否符合
```
references/findings-schema.md
```
。
按严重程度分组；包含范围元数据（
```
engagement_id
```
、
```
target
```
、ROE哈希值）。
标准化操作人员提供的记录时，使用
```
scripts/findings_emit.py --aggregate
```
。
执行摘要必须说明授权依据及已遵守的禁止操作。

Mode: help

模式：help

Show dispatch table, scope gate steps, and tier boundary table.
List reference files with read-when guidance.
Remind: this skill does not install Strix or other runners — see
```
references/external-runners.md
```
.

展示调度表、scope gate步骤及层级边界表。
列出参考文件及读取时机指引。
提醒：本技能不会安装Strix或其他运行工具——详见
```
references/external-runners.md
```
。

Help (empty)

帮助（空参数）

Show dispatch table, scope gate steps, tier boundaries, and reference index. Offer examples:

text

/pentest help
/pentest doctor
/pentest scope staging.example.com
/pentest recon staging.example.com
/pentest web https://staging.example.com/app
/pentest api https://staging.example.com/api
/pentest osint staging.example.com
/pentest validate
/pentest report

展示调度表、scope gate步骤、层级边界及参考索引。提供示例：

text

/pentest help
/pentest doctor
/pentest scope staging.example.com
/pentest recon staging.example.com
/pentest web https://staging.example.com/app
/pentest api https://staging.example.com/api
/pentest osint staging.example.com
/pentest validate
/pentest report

Reference File Index

参考文件索引

Load ONE reference at a time. Do not preload all references.

File	Content	Read When
`references/scope-and-roe.md`	ROE format, scope gate policy, deny reasons	Scope deny or ROE questions
`references/findings-schema.md`	JSON finding fields and severity rules	Emitting or validating findings
`references/methodology-router.md`	Compact signal → playbook → slug routing	`triage` or depth routing
`references/external-skill-index.manifest.json`	Pointer to planning-lock full index	Operator requests upstream body
`references/playbooks/*.md`	Phase and technique checklists (22 files)	Matching phase after scope pass
`references/osint.md`	Passive OSINT templates (legacy index)	`recon` or `osint` after scope pass
`references/provenance.md`	Synthesis sources, hybrid repos, no C2 policy	Methodology questions or audit trail
`references/external-runners.md`	Optional external CLIs (Strix, etc.) — no install	Operator asks about tooling

一次仅加载一个参考文件。不得预加载所有参考文件。

文件	内容	读取时机
`references/scope-and-roe.md`	ROE格式、scope gate政策、拒绝原因	范围校验拒绝或ROE相关问题
`references/findings-schema.md`	JSON测试结果字段及严重程度规则	输出或验证测试结果时
`references/methodology-router.md`	紧凑的信号→操作手册→标识路由	`triage` 或深度路由时
`references/external-skill-index.manifest.json`	指向规划锁完整索引的指针	操作人员请求上游内容时
`references/playbooks/*.md`	阶段及技术检查清单（22个文件）	通过范围校验后的匹配阶段
`references/osint.md`	被动OSINT模板（旧版索引）	通过范围校验后的 `recon` 或 `osint` 模式
`references/provenance.md`	整合来源、混合仓库、无C2政策	方法论问题或审计追踪时
`references/external-runners.md`	可选外部CLI（如Strix）——无安装指引	操作人员询问工具时

Scripts

脚本列表

Script	When to Run
`scripts/phases.py`	SSOT for `VALID_PHASES` (imported by scope/findings)
`scripts/scope_check.py`	Always before offensive planning — fail-closed without ROE
`scripts/doctor.py`	`doctor` mode or pre-engagement readiness
`scripts/findings_emit.py`	Emit or aggregate structured findings JSON (schema v1.1)
`scripts/lookup_external_slug.py`	Resolve signal/slug install metadata from planning lock
`scripts/validate_external_index.py`	Maintainer check for planning-lock index policy
`scripts/check.py`	`validate` mode or CI/skill maintenance

脚本	运行时机
`scripts/phases.py`	`VALID_PHASES` 的单一可信来源（被范围/测试结果模块导入）
`scripts/scope_check.py`	必须在进攻性规划前运行——无ROE则触发闭环拒绝
`scripts/doctor.py`	`doctor` 模式或测试前就绪检查
`scripts/findings_emit.py`	输出或聚合结构化测试结果JSON（schema v1.1）
`scripts/lookup_external_slug.py`	从规划锁中解析信号/标识的安装元数据
`scripts/validate_external_index.py`	维护人员检查规划锁索引政策
`scripts/check.py`	`validate` 模式或CI/技能维护

Critical Rules

核心规则

Scope gate first — no recon, web, api, or osint planning without passing
```
scope_check.py
```
Fail-closed — missing
```
--target
```
or
```
--roe-file
```
denies immediately
No attack execution in scripts — bundled Python is planning, validation, and JSON only
No C2 or webshell vendoring — refuse requests for implants, reverse shells, or malware staging
No unauthorized testing — without signed ROE, redirect to security-scanner (static) or refuse
CTF is not pentest — redirect synthetic lab work to ctf-* skills
Operator-run tools only — cite commands for the operator; skill scripts do not probe targets
Respect ROE phases — deny playbooks when phase not in
```
allowed_phases
```
Respect prohibited_actions — DOS, social engineering, production data exfiltration when banned

Structured findings — use

findings_emit.py

and

references/findings-schema.md

Load ONE reference at a time — progressive disclosure
Present plan before deep checklist — approval gate for invasive operator steps
Never store live credentials — redact secrets in findings and reports
External runners are optional — document in
```
external-runners.md
```
; never auto-install Strix
Read-only ROE — scripts validate ROE files; they do not create or modify authorization

先过scope gate——未通过
```
scope_check.py
```
校验，不得进行recon、web、api或osint规划
闭环拒绝——缺少
```
--target
```
或
```
--roe-file
```
立即拒绝
脚本不执行攻击——捆绑Python脚本仅用于规划、验证及JSON处理
不提供C2或webshell——拒绝植入程序、反向shell或恶意软件 staging 请求
禁止未授权测试——无签署的ROE则重定向到security-scanner（静态）或直接拒绝
CTF不等于渗透测试——合成实验室工作重定向到ctf-*技能
仅操作人员运行工具——为操作人员提供命令参考；技能脚本不会探测目标
遵守ROE阶段限制——当阶段不在
```
allowed_phases
```
中时，拒绝加载操作手册
遵守禁止操作——禁止时不得执行DOS、社会工程、生产数据泄露等操作

结构化测试结果——使用

findings_emit.py

及

references/findings-schema.md

一次加载一个参考文件——渐进式披露
先展示计划再提供详细检查清单——操作人员执行侵入性步骤前需确认
绝不存储实时凭证——测试结果及报告中需脱敏密钥
外部运行工具为可选——在
```
external-runners.md
```
中记录；绝不自动安装Strix
ROE只读——脚本仅验证ROE文件；不创建或修改授权文档