develop-disguise SKILL.md skillA

develop-disguise from cha0upup/leoai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cha0upup/leoai/develop-disguise@git:20261001.e4dd21a

Pins git:20261001.e4dd21a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cha0upup/leoai
Path
root/skills/platform/develop-disguise/SKILL.md
Versions recorded
6
Latest version
git:20261001.e4dd21a, committed Oct 1, 2026
First version recorded
Jun 16, 2026
Size
10,577 bytes
Repository stars
331
License
GPL-3.0

当用户希望在平台侧开发、测试、创建或更新 Disguise 时使用。该 skill 用于生成符合平台约束的 trafficEncodeBody、trafficDecodeBody、headersJson、description 和规范名称,并优先调用 testDisguise 验证 traffic 编解码是否可互逆,再创建或更新 Disguise。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 开发平台侧 Disguise

当用户要求开发、修改、测试、完善或保存 Disguise 时,使用这个 skill。

## 职责边界

| 侧 | trafficEncode(出站) | trafficDecode(入站) |
|---|---|---|
| 平台侧 | PayloadCodec 序列化/压缩/加密,再经 trafficEncodeBody 伪装 | 先经 trafficDecodeBody 还原字节,再由 PayloadCodec 解密/解压/反序列化 |
| agent 侧 | PayloadCodec 序列化/压缩/加密,再经 trafficEncodeBody 伪装 | 先经 trafficDecodeBody 还原字节,再由 PayloadCodec 解密/解压/反序列化 |

平台侧 `trafficEncodeBody` 和 `trafficDecodeBody` 只处理不透明字节,必须与 agent 侧协议严格匹配,且在平台侧测试逻辑下必须可互逆。

---

## 一、核心约束

### 1.1 方法签名(不可更改)

```java
public byte[] encodeTraffic(byte[] payload) throws Exception
public byte[] decodeTraffic(byte[] body) throws Exception
```

### 1.2 互逆性

`decodeTraffic(encodeTraffic(bytes))` 必须返回与输入完全相等的任意字节序列。序列化、压缩和加密由固定 `PayloadCodec` 负责。

### 1.3 单次保存

- 一次请求中只允许调用 **一次** `addDisguise` 或 `updateDisguise`。
- 中间草案只能存在于上下文或通过 `testDisguise` 验证,不得保存。
- 若已保存成功,后续想调整命名/headers/description,应告知用户可在同一 `disguiseId` 上更新,不要新建第二个。
- 比较多个候选时只输出草案,用户选定后保存唯一一个。

### 1.4 测试先行

保存前 **必须** 调用 `testDisguise`。测试未通过时禁止调用 `addDisguise` / `updateDisguise`。

### 1.5 依赖限制

- 只使用 JDK 内部类,不引入第三方库。
- 语法版本尽可能低:不使用 lambda、record、text block、switch 新语法,除非用户明确要求且确认兼容。

### 1.6 安全与审计

- `description` / `remark` 必须包含授权测试、协议适配、兼容性验证或检测验证用途说明。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cha0upup/leoai/develop-disguise@sha256:6e1b5bf49146883a

The line at the top of this page pins the label git:20261001.e4dd21a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_me724em6cg5ny735.svg)](https://markdownregistry.com/a/art_me724em6cg5ny735)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Jun 16, 2026 and Oct 1, 2026, about one every 21 days.

versioncommittedcommitsizeaudit
git:20261001.e4dd21a latest2026-10-01 e4dd21a 10,577 BA view · diff
git:20260820.9149adf2026-08-20 9149adf 10,580 BA view · diff
git:20260811.eedfbb72026-08-11 eedfbb7 13,107 BA view · diff
git:20260803.d1bb1222026-08-03 d1bb122 13,269 BA view · diff
git:20260801.6c9c1292026-08-01 6c9c129 13,256 BA view · diff
git:20260616.da8811e2026-06-16 da8811e 13,288 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10577 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

cha0upup/leoai · 331 stars · license GPL-3.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_me724em6cg5ny735
GET https://markdownregistry.com/api/v1/resolve?ref=cha0upup/leoai/develop-disguise
GET https://markdownregistry.com/api/v1/blob/6e1b5bf49146883a2523dd7499a2d9adf22cdfa61ac7c259b68365abeb416d4a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from cha0upup/leoai

analyze-browser-artifacts SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/agent-node/analyze-browser-artifacts/SKILL.md · 发现当前 Agent 用户的浏览器 Profile,对书签、历史、Cookie、表单和登录数据库建立一致性副本,将选定制品采集到当前 AI 工作空间,并使用工作空间命令与文件工具解析为可搜索的结构化报告。当用户要求分析浏览器数据、时间线、访…
git:20261001.e4dd21a · audit A · 331 stars
escalate-linux-privilege SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/agent-node/escalate-linux-privilege/SKILL.md · 在 Linux Agent 立足点上以只读方式发现并排序本地提权候选路径,覆盖 sudo、SUID/SGID、cron、PATH、服务、容器、Docker socket、NFS…
git:20261001.e4dd21a · audit A · 331 stars
hunt-credentials SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/agent-node/hunt-credentials/SKILL.md · 在已授权的 Agent 立足点上定向搜集与红队任务相关的应用、JVM、数据库、SSH、云和服务账号凭据线索,建立“凭据—身份—目标—用途”映射。当需要扩大访问、接近指定业务目标或判断当前主机凭据价值时使用。
git:20261001.e4dd21a · audit A · 331 stars
lateral-move-ssh SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/agent-node/lateral-move-ssh/SKILL.md · 使用已授权且已匹配的 SSH 私钥,对明确指定的内网 Linux 目标执行单跳登录和最小分诊,验证能否获得对任务有价值的新立足点。当红队人员已有目标、用户名、私钥路径并明确要求横向验证时使用;不得用于密码喷洒、用户名猜测或自动多跳。
git:20261001.e4dd21a · audit A · 331 stars
persistence-linux SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/agent-node/persistence-linux/SKILL.md · 在管理员显式启用、演练 ROE 允许且用户精确授权后,为 Linux Agent 目标部署一项与红队任务匹配、可验证、限时且可完整回滚的持久化机制。当需要在既定存续窗口内维持对指定账号或主机的访问,并已提供载荷、路径和清理要求时使用。
git:20261001.e4dd21a · audit A · 331 stars
recon-basic-info SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/agent-node/recon-basic-info/SKILL.md · 对新的 Agent 立足点执行低噪声基础侦察,判断当前权限、业务价值、网络位置、关键服务、容器边界和可用行动入口,并形成红队主机画像。当进入新目标、需要判断立足点价值或尚无可靠侦察摘要时使用。
git:20261001.e4dd21a · audit A · 331 stars
develop-disguise SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/platform/develop-disguise/SKILL.md · 当用户希望在平台侧开发、测试、创建或更新 Disguise 时使用。该 skill 用于生成符合平台约束的 trafficEncodeBody、trafficDecodeBody、headersJson、description…
git:20261001.e4dd21a · audit A · 331 stars
develop-fingerprint SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/platform/develop-fingerprint/SKILL.md · 当用户希望在平台侧编写、生成、完善、检查、保存、更新或删除指纹规则时使用。指纹由 NetworkProbe 采集证据,服务侧使用声明式 rule.match 判定。
git:20260918.5a4ff65 · audit A · 331 stars
exploit-suggest SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/platform/exploit-suggest/SKILL.md · 当用户希望基于命中的指纹获取后续核查建议时使用。根据已识别组件、实测版本和独立的安全公告评估适用条件,输出有来源的建议,不直接执行利用动作。
git:20260918.5a4ff65 · audit A · 331 stars
shell-obfuscation SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/platform/shell-obfuscation/SKILL.md · 理解 LeoAI Java/PHP WebShell 与 Java 内存马生成链路,根据用户本次选择的通信、伪装、兼容性和混淆参数生成独立制品。用户要求生成、变体生成、调整兼容性或排查 Shell 无法连接时使用;始终通过…
git:20261001.e4dd21a · audit A · 331 stars
develop-fingerprint SKILL.md skill
cha0upup/leoai · root/skills/platform/develop-fingerprint/SKILL.md · 当用户希望在平台侧编写、生成、完善、检查、保存、更新或删除指纹规则时使用。指纹由 NetworkProbe 采集证据,服务侧使用声明式 rule.match 判定。
git:20260918.5a4ff65 · audit A · 331 stars
exploit-suggest SKILL.md skill
cha0upup/leoai · root/skills/platform/exploit-suggest/SKILL.md · 当用户希望基于命中的指纹获取后续核查建议时使用。根据已识别组件、实测版本和独立的安全公告评估适用条件,输出有来源的建议,不直接执行利用动作。
git:20260918.5a4ff65 · audit A · 331 stars

Every file in cha0upup/leoai

Other files named develop-disguise

develop-disguise SKILL.md skill
cha0upup/leoai · ai/src/main/resources/skills/platform/develop-disguise/SKILL.md · 当用户希望在平台侧开发、测试、创建或更新 Disguise 时使用。该 skill 用于生成符合平台约束的 trafficEncodeBody、trafficDecodeBody、headersJson、description…
git:20261001.e4dd21a · audit A · 331 stars

Browse by kind, by grade A, or by owner.