Agent skill · Audited from source
huashu-agent-swarm
skill · alchaincyf/huashu-skillsMIT licenceAudited 20 Oct 2026 · source 523a72c98cf8
Is it safe? No — BLOCK, grade D (69/100). We read this skill's source at commit 523a72c98cf8 and observed shell access and no hard-coded secrets. The audit raised 2 findings, 1 critical or high. What it does: 多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。
Cite
Cite this page
ModelsAtlas. “huashu-agent-swarm (alchaincyf/huashu-skills)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/alchaincyf/huashu-agent-swarm
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 “Privilege escalation / persistence” in scripts/start_swarm.sh:21. Do not install it without reading them.
Trust audit
Audit 0.4.1 · source read 20 Oct 2026
BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 642 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellDeclared1 observation
- 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 | FAIL | 1 |
L2 Instructions | Prompt injection, authority framing, hidden directives | WARN | 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: no behavioural pass.
Findings (2)
HIGHPrivilege escalation / persistencepriv.escalate · scripts/start_swarm.sh:21
echo " Ubuntu: sudo apt install tmux"
- Why
- asks for elevated privileges
- Fix
- —
MEDIUMPrompt injectionscope.undeclared_system · <declared scope>
system use found in code, not declared in the description
- Why
- the description does not admit a capability the code has
- Fix
- declare system use in the description, or remove it
Audit 0.4.1 · source sha 523a72c98cf8 · 20 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheralchaincyf GitHub userOwner of the repository this skill is read from
- Source folderalchaincyf/huashu-skills/huashu-agent-swarmThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict523a72c98cf8A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: 多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。
--- name: huashu-agent-swarm description: 多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。 --- # Infinite Agent Loop - 无限Agent蜂群模式 > 受Nicholas Carlini用16个Claude实例自主构建C编译器的启发。 > 没有master agent,纯git自组织,每个agent独立认领任务、写代码、推送。 ## 触发条件 当用户提到「蜂群模式」「多agent并行」「infinite loop」「agent swarm」「启动蜂群」时使用此技能。 ## 前置要求 - tmux(`brew install tmux`) - claude CLI(已安装) - git 仓库(已有或新建) ## 使用流程 ### Step 1: 描述项目 用户告诉我: - 项目目录路径(必须是git仓库) - 项目目标和总体描述 - 初始任务列表(或让agent自行拆解) - agent数量(默认8个) - 代码规范和测试命令 ### Step 2: 初始化项目 ```bash bash SKILL_DIR/scripts/setup_project.sh <项目目录> ``` 这会在项目中创建: - `AGENT_PROMPT.md` - 从模板生成,需要我根据用户需求定制 - `TASKS.md` - 初始任务清单 - `current_tasks/` - 任务认领目录 - `agent_logs/` - 日志目录 然后我根据 `references/agent-prompt-template.md` 定制 `AGENT_PROMPT.md`,填入项目具体信息。 ### Step 3: 启动蜂群 ```bash bash SKILL_DIR/scripts/start_swarm.sh <agent数量> <项目目录> ``` 这会: 1. 为每个agent创建 git worktree(共享.git对象库,不浪费磁盘) 2. 创建 tmux session,每个pane一个agent 3. 每个agent进入无限循环:pull → 认领任务 → 执行 → push → 下一个 ### Step 4: 打开观测台 ```bash python3 SKILL_DIR/scripts/dashboard.py <项目目录> 8420 ``` 浏览器打开 http://localhost:8420,可以: - 实时查看所有agent状态、git log、任务进度 - 查看每个agent的最新日志 - 输入框直接发送指令给agent(写入HUMAN_INPUT.md) - 一键停止所有agent 也可以用命令行监控: ```bash # 终端状态 bash SKILL_DIR/scripts/status.sh <项目目录> # 发送指令 bash SKILL_DIR/scripts/send_input.sh <项目目录> "你的指令" # 直接进入tmux观察 tmux attach -t swarm-<项目名> ``` ### Step 5: 停止 ```bash bash SKILL_DIR/scripts/stop_swarm.sh <项目目录> ``` 自动停止所有agent + 合并分支 + 清理worktrees。 ## 核心机制 ### Git自组织协调 - 每个agent通过 `current_tasks/*.lock` 文件认领任务 - 通过 `TASKS.md` 了解全局进度 - 通过 `git log` 了解其他agent的工作 - 冲突由agent自行解决 ### Git Worktree隔离 - 不用多份clone,用 `git worktree` 实现隔离 - 所有worktree共享同一个 `.git` 对象库 - 每个agent在自己的worktree独立工作 ### 无限循环 - 每个agent完成一个session后自动开始下一个 - 通过 `git pull` 获取其他agent的最新成果 - 通过 sleep 间隔避免API限流 ## 关键配置 | 参数 | 默认值 | 说明 | |------|--------|------| | agent数量 | 8 | 可在启动时指定 | | sleep间隔 | 5秒 | agent_loop.sh中可调 | | 模型 | claude-opus-4-6 | agent_loop.sh中可调 | ## 风险和应对 | 风险 | 应对 | |------|------| | API限流 | sleep间隔 + 可调agent数量 | | 合并冲突 | AGENT_PROMPT指导小粒度commit | | 死循环无用功 | 日志监控 + 停止条件 | | 磁盘空间 | stop_swarm.sh自动清理 | | 成本失控 | 可在AGENT_PROMPT中限制session数 | --- > **花叔出品** | AI Native Coder · 独立开发者 > 公众号「花叔」| 30万+粉丝 | AI工具与效率提升 > 代表作:小猫补光灯(AppStore付费榜Top1)·《一本书玩转DeepSeek》
Excerpt, first 2,301 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 523a72c
git clone https://github.com/alchaincyf/huashu-skills git -C huashu-skills checkout 523a72c98cf8
The author documents no install command, so this uses the repository directly. Our verdict covers commit 523a72c98cf8 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✕BLOCK D 69 / 100
first audit · source
523a72c98cf8
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/alchaincyf/huashu-agent-swarm/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
obra/superpowers
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
obra/superpowers
Use when implementing any feature or bugfix, before writing implementation code
obra/superpowers
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Add this badge to your README
[](https://modelsatlas.com/skills/alchaincyf/huashu-agent-swarm/)
<a href="https://modelsatlas.com/skills/alchaincyf/huashu-agent-swarm/"><img src="https://modelsatlas.com/skills/alchaincyf/huashu-agent-swarm/badge.svg" alt="ModelsAtlas: BLOCK D"></a>
Questions about huashu-agent-swarm
What does the huashu-agent-swarm skill do?
Is huashu-agent-swarm safe to install?
What can huashu-agent-swarm access on my machine?
How current is this page?
Sources
- github.com/alchaincyf/huashu-skills/tree/master/huashu-agent-swa — the audited source at commit 523a72c98cf8 and every finding aboveObserved · 20 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 huashu-agent-swarm skill do?
- Is huashu-agent-swarm safe to install?
- What can huashu-agent-swarm access on my machine?