huashu-agent-swarm
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。
68
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
代码明确设计为让LLM代理以 --dangerously-skip-permissions 模式自主运行并执行任意shell/git操作，同时通过一个对外HTTP控制台接收命令和触发合并/推送，构成远程代码执行、命令注入和潜在数据外泄的高风险后门/滥用渠道。
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
在 `scripts/dashboard.py` 的 HTTP 接口 `/api/input` 中接收外部文本并写入项目内的 `HUMAN_INPUT.md`，而 `references/agent-prompt-template.md` 指定每个 agent session 开始时会读取该文件内容优先执行，因此 outsider 可通过该运行时输入通道向被管理的 LLM 注入任意指令。
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill runs git pull at runtime ("git pull --rebase origin main") and then injects the repo file AGENT_PROMPT.md into the Claude prompt (via cat AGENT_PROMPT.md), so remote repository content fetched from "git pull --rebase origin main" can directly control agent instructions and cause execution of actions; this is a high-confidence runtime external dependency.
- Repository
- alchaincyf/huashu-skills
- Commit
35e7cf3
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.