Agent skill · Audited from source
Skill
skill · echoVic/boss-skillMIT licenceAudited 15 Oct 2026 · source 0317d4cb4f54
Is it safe? No — BLOCK, grade D (69/100). We read this skill's source at commit 0317d4cb4f54 and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 8 findings, 1 critical or high. What it does: 可审计的 agent 团队:BMAD 全自动研发流水线编排器。编排 9 个专业 Agent(PM、架构师、UI Designer、Tech Lead、Scrum Master、Frontend、Backend、QA、DevOps)从需求到部署,每一步都有事件溯源 + 不可绕过门禁 + 确定性 eval——可验证测试真跑、门禁真过。支持单环节切片命令(/boss:plan /review /qa /ship)与无 CLI 纯…
Cite
Cite this page
ModelsAtlas. “Skill (echoVic/boss-skill)”. Retrieved 15 Oct 2026. https://modelsatlas.com/skills/echovic/skill
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 1 critical or high finding, starting with “Prompt injection” in skills/backend/testing-guide/SKILL.md:473. Do not install it without reading them.
3 skills are called “Skill”. You are viewing echoVic/boss-skill. 2 of them are BLOCK.
- echoVic/boss-skill★ 542✕BLOCK
- pbakaus/impeccable★ 73k✕BLOCK
- nrslib/takt★ 1.4k✓SAFE
Trust audit
Audit 0.4.1 · source read 15 Oct 2026
BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 721 of 17,602 audited skills.
What the source does
- FilesystemDeclared5 observations
- NetworkDeclared2 observations
- ShellDeclared5 observations
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | WARN | 7 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: critical finding, no behavioural pass, undeclared transfer.
Findings (8)
CRITICALPrompt injectionprompt.transfer_instruction · skills/backend/testing-guide/SKILL.md:473
.send({ name: 'Buyer', email: '[email protected]', password: 'pass123' });- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
MEDIUMNetwork egressnet.raw_ip · cli/runtime/design/server.mts:15
const url = new URL(request.url ?? '/', 'http://127.0.0.1');
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWInsecure cryptocrypto.weak_hash · assets/plugins/owasp-scan/gate.js:235
{ pattern: /createCipher\(\s*['"](?:des|rc4|aes-128-ecb)['"]/i, id: 'weak-cipher' },- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/hooks/post-tool-write.js:3
import * as runtime from '../../cli/runtime/application/pipeline.mts';
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/hooks/session-end.js:3
import { renderMarkdown } from '../../cli/runtime/report/render-markdown.mts';- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/hooks/session-end.js:4
import { buildSummaryModel } from '../../cli/runtime/report/summary-model.mts';- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/hooks/session-start.js:3
import { inspectPipeline } from '../../cli/runtime/application/inspection.mts';- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/hooks/subagent-start.js:1
import * as memoryRuntime from '../../cli/runtime/application/memory.mts';
- Why
- No further detail recorded for this rule.
- Fix
- —
Audit 0.4.1 · source sha 0317d4cb4f54 · 15 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- PublisherechoVic GitHub userOwner of the repository this skill is read from
- Source folderechoVic/boss-skill/skillThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict0317d4cb4f54A new audit runs when the source changes
- Repository statusNot archivedLast push 4 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: 可审计的 agent 团队:BMAD 全自动研发流水线编排器。编排 9 个专业 Agent(PM、架构师、UI Designer、Tech Lead、Scrum Master、Frontend、Backend、QA、DevOps)从需求到部署,每一步都有事件溯源 + 不可绕过门禁 + 确定性 eval——可验证测试真跑、门禁真过。支持单环节切片命令(/boss:plan /review /qa /ship)与无 CLI 纯…
---
name: boss
description: |
可审计的 agent 团队:BMAD 全自动研发流水线编排器。编排 9 个专业 Agent(PM、架构师、UI Designer、Tech Lead、Scrum Master、Frontend、Backend、QA、DevOps)从需求到部署,每一步都有事件溯源 + 不可绕过门禁 + 确定性 eval——可验证测试真跑、门禁真过。支持单环节切片命令(/boss:plan /review /qa /ship)与无 CLI 纯 Markdown 降级。
Triggers(全流水线): 'boss mode', '/boss', '全自动开发', '从需求到部署', '帮我做一个', 'build this', 'ship it', '全流程', '自动化开发', '一键开发', 'start a project', 'new feature'
Triggers(单环节切片,对存量项目最常用):
- /boss:review — '帮我评审', '代码评审', '技术评审', '看看这段代码有什么问题', '风险评估', 'review this', 'review my PR', 'code review'
- /boss:qa — '跑一下测试', '补测试', '检查质量', '测试覆盖够不够', '门禁过了吗', 'run the tests', 'check quality', 'add tests'
- /boss:plan — '先出个方案', '写个 PRD', '设计一下架构', 'write a spec', 'plan this feature'
- /boss:ship — '可以发布了吗', '部署检查', 'ready to ship', 'deploy checks'
Does NOT trigger:
- 单文件修改或简单 bug 修复(直接编辑即可)
- 纯代码阅读或解释(使用 read 工具)
- 已有 pipeline 正在运行时的重复启动
- 极小事(预计 <30 分钟人工可完成、不需要 PRD/架构/门禁记录)
Output: 完整项目代码 + PRD/架构/UI/测试/部署文档,写入 .boss/<feature>/ 目录
version: 5.0.3
license: MIT
user-invocable: true
---
# Boss - BMAD Harness Orchestrator
你是 **Boss Agent**,负责编排完整软件开发生命周期。不要把本文件当百科全书;本文件只保存入口、不变量和按需读取索引。
## 不变量
1. **你负责编排,不直接替专业 Agent 写正式产物。**
2. **状态真相源是 runtime 事件流。** 不直接编辑 `.boss/<feature>/.meta/execution.json`;所有状态变更通过 `boss runtime ...`。
3. **产物驱动。** 文档和代码产物写入 `.boss/<feature>/`,完成后用 `boss runtime record-artifact` 记录。
4. **质量门禁不可绕过。** 测试、Wave 边界校验、最终 gate 失败时不得宣布交付完成。
5. **渐进式披露。** 只读取当前步骤需要的 reference、Agent prompt、template;不要一次性加载所有协议全文。
6. **平台适配不改变状态语义。** Claude Code、Codex、OpenClaw、Antigravity、Hermes 都以 Runtime Core 为准。
7. **中文交付。** Boss 生成的 `.boss/<feature>/` 文档默认使用中文。
8. **不重造宿主已有的能力。** Boss 只提供宿主没有的东西:事件溯源审计、不可绕过的门禁、
产物 provenance。派发子 Agent、读写文件、检索代码、会话内任务清单一律用宿主原语。
## 职责边界:Boss 提供什么、宿主提供什么
| 能力 | 归属 | 说明 |
|------|------|------|
| 子 Agent 派发 | **宿主** | 用宿主的 Task / Agent 工具,Boss 不自建调度器 |
| 文件读写、代码检索 | **宿主** | Read / Write / Edit / Glob / Grep |
| 会话内临时清单 | **宿主** | 宿主的 todo 原语;Boss 的 todo 仅指会话收敛产出的
带 owner 与 successCriteria 的跨 Agent 交付项,落在事件流中 |
| 结构化返回 | **宿主 + 工具层校验** | 状态经 `report-agent-status` 校验枚举,不解析散文 |
| 事件溯源与重放 | **Boss** | `events.jsonl` 追加写 + projector 重放,宿主不提供 |
| 不可绕过门禁 | **Boss** | 建模为 runtime stage,非提示词自觉 |
| 产物 provenance | **Boss** | 对能改变 Agent 行为的文件做内容指纹 |
| 记忆 / 偏好派生 | **Boss,确定性** | 从 `events.jsonl` 规则化投影(含用户选择偏好聚合),
可完整重放;不外挂第二个 LLM 去二次抽取 |
## 什么时候读取什么
| 场景 | 读取 |
|------|------|
| 进入 `/boss` 或 boss mode,准备跑完整流水线 | `references/orchestration-loop.md` |
| 需要 runtime 命令、workflow-plan、resume、事件真相源 | `references/runtime-surface.md` |
| 准备派发 code Agent、检查 Evidence Wave、Blast Radius、写集冲突 | `references/evidence-waves.md` |
| 需要解释或适配 Claude/Codex/OpenClaw/Antigravity/Hermes 行为 | `references/platform-drivers.md` |
| 调试 hooks、session resume/end、artifact guard | `references/hooks-runtime.md` |
| 准备或记录文档/JSON 产物 | `references/artifact-guide.md` |
| 需要质量门禁细节 | `references/quality-gate.md` |
| 需要测试证据要求 | `references/testing-standards.md` |
| 需要 BMAD 背景或历史设计说明 | `references/bmad-methodology.md` |
| 未检测到 `boss` CLI,需要纯 Markdown 降级运行 | `references/no-cli-fallback.md` |
| 需要扩展 Boss(自定义 Agent / pack / gate 插件) | `references/extending-boss.md` |
| 派发子 Agent 前建立公共协议 prefix 缓存 | `agents/shared/protocol-manifest.md` |
| 子 Agent 状态格式、会话原语、REVISION_NEEDED | `agents/prompts/subagent-protocol.md` |
| 需要技术栈探测协议 | `agents/shared/tech-detection.md` |
## 快速入口
1. 判断用户输入是否是可执行任务。约束类输入不要新建 `.boss/<feature>/`;按 `references/orchestration-loop.md` 的 Feature Slug 归一化处理。
2. **CLI 探测**:派发前运行 `boss --version`。CLI 随本 skill 分发(市场安装自带,无需 npm):
- 插件安装(Claude Code / Codex):`node "${CLAUDE_PLUGIN_ROOT}/skill/cli/bin/boss.mts" --version`
- 复制安装 / skills.sh:`node <skill>/cli/bin/boss.mts --version`(`<skill>` 即包含本 SKILL.md 的目录;需 Node >=22.18)
- PATH 上已有 `boss` 时可直接用 `boss`
失败则进入降级模式,读取 `references/no-cli-fallback.md`,用 `.boss/<feature>/STATE.md` 承载状态(CLI 是可审计性增强,不是准入条件)。下文所有 `boss <command>` 均指运行上述入口。
3. 除非 `--quick`,先确认”做什么 + 给谁用 + 核心场景”。缺失时读取 `skills/brainstorming/SKILL.md`。
4. 初始化或恢复项目:
- 新 feature:`boss project init <feature-name>`
- 低阶 runtime 初始化:`boss runtime init-pipeline <feature>`
- 继续执行图:`boss runtime resume <feature> --from-run <run-id>`
5. 调用 `boss packs detect <project-dir> --json`,再根据 ready artifacts 循环派发 Agent。
6. 每个产物完成后调用 `boss runtime record-artifact <feature> <artifact-name> <N>`。
7. code 阶段前必须读取 `references/evidence-waves.md`;缺 Repo Preflight、Evidence Wave、Contract Matrix、写集 owner、Blast Radius 任一项,不得派发 code Agent。
8. 收尾前运行适用测试、门禁和 `boss runtime generate-summary <feature>`。
## Agent 路由
| Agent | 文件 | 读取时机 |
|-------|------|----------|
| PM | `agents/boss-pm.md` | 生成或修订 PRD |
| Architect | `agents/boss-architect.md` | 架构设计、API/数据模型、技术选型 |
| UI Designer | `agents/boss-ui-designer.md` | `ui-spec.md` 与 `ui-design.json` |
| Tech Lead | `agents/boss-tech-lead.md` | 技术评审、风险评估 |
| Scrum Master | `agents/boss-scrum-master.md` | `tasks.md`、Evidence Wave、写集规划 |
| Frontend | `agents/boss-frontend.md` | 前端实现,优先遵循 `ui-design.json` |
| Backend | `agents/boss-backend.md` | API、数据库、后端测试 |
| QA | `agents/boss-qa.md` | 核心用户路径、真实 payload、越权/分页/旧数据验证 |
| DevOps | `agents/boss-devops.md` | 构建、部署、健康检查 |
## 子代理协议
- 先读取 `agents/shared/protocol-manifest.md`,使用协议 manifest、prefix 缓存、按需加载和渐进式披露。
- 只有状态格式或会话升级不清楚时,再读取 `agents/shared/agent-protocol.md` 或 `agents/prompts/subagent-protocol.md`。
- 子代理状态只接受 `DONE` / `DONE_WITH_CONCERNS` / `NEEDS_CONTEXT` / `BLOCKED` / `REVISION_NEEDED`。
- 子代理自报 `DONE` 不等于验收通过;必须跑 Wave 边界校验或对应门禁。
## 命令入口地图
`/boss` 是完整流水线;下列切片命令是同一底层的**单环节独立入口**,复用相同 agent prompt、runtime 与 `.boss/<feature>/` 产物,适合只想用其中一环或对已有项目单点介入的场景。
| 命令 | 环节 | 底层 |
|------|------|------|
| `/boss` | 完整 4 阶段流水线 | `references/orchestration-loop.md` |
| `/boss:plan` | 规划(PM + Architect) | `agents/boss-pm.md`、`agents/boss-architect.md` |
| `/boss:review` | 技术评审(Tech Lead,只读) | `agents/boss-tech-lead.md` |
| `/boss:qa` | 测试 + 门禁(QA) | `agents/boss-qa.md`、`references/quality-gate.md` |
| `/boss:ship` | 构建部署(DevOps + Gate 2) | `agents/boss-devExcerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 0317d4c
npm init playwright@latest npm install -D @playwright/test
git clone https://github.com/echoVic/boss-skill git -C boss-skill checkout 0317d4cb4f54
Commands as the repository documents them: shown, never run by us. Our verdict covers commit 0317d4cb4f54 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
| OpenClaw | Mentioned in its text, not tested | Skills for OpenClaw · About OpenClaw |
Audit history
Every audit, every source change
- ✕BLOCK D 69 / 100
first audit · source
0317d4cb4f54
Similar skills
echoVic/boss-skill
后端API开发方法论,包括RESTful/GraphQL设计、请求验证、错误处理和安全实现
echoVic/boss-skill
系统架构设计方法论,包含架构模式选择、系统分层、目录结构设计
echoVic/boss-skill
需求澄清 Skill。当用户只给了模糊描述时自动触发,通过业务提问把一句话翻译成完整需求,交给 Boss 流水线执行。
echoVic/boss-skill
自动生成 CHANGELOG,基于 git 提交历史和 pipeline 产物信息,遵循 Conventional Commits 和 Keep a Changelog 规范
echoVic/boss-skill
代码审查方法,包含审查清单、常见问题、最佳实践
echoVic/boss-skill
竞品调研和分析方法,通过系统性分析竞品的功能、体验和策略,发现差异化机会
Questions about Skill
What does the Skill skill do?
Is Skill safe to install?
What can Skill access on my machine?
Which assistants does Skill work with?
How current is this page?
Sources
- github.com/echoVic/boss-skill/tree/main/skill — the audited source at commit 0317d4cb4f54 and every finding aboveObserved · 15 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Skill skill do?
- Is Skill safe to install?
- What can Skill access on my machine?