技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.5
统计：⭐ 0 · 537 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：可疑
Package：armandobrazil/humanod
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：可疑
OpenClaw 评估
The skill's stated purpose (hiring humans) matches the provided tools and API, but there are multiple inconsistencies and a prompt-injection signal that warrant caution before installing or supplying credentials.
目的
The skill claims to let agents hire humans and the SKILL.md/openapi define appropriate endpoints and a HUMANOD_API_KEY. However the registry metadata reported no required credentials (contradiction), the OpenAPI server points to humanod-api.onrender.com (a render.com host) while the docs/domains in SKILL.md reference humanod.app/docs, and there is no homepage or established source. These mismatches reduce confidence in provenance.
说明范围
The included system prompt forces the agent to request the API key at the start and append it to every API call. While that supports the skill's function, the presence of a 'system-prompt-override' injection pattern (scanner flag) is concerning because system prompts can change agent behavior beyond normal tool usage. Also the system prompt's instruction to append the key as a query parameter could increase accidental exposure (logging, refere…
安装机制
This is instruction-only with no install spec and no code files — lowest technical risk from installation. Nothing is written to disk by an installer.
证书
The skill reasonably needs a single HUMANOD_API_KEY to operate. However the registry metadata lists no required env vars or primary credential while SKILL.md and system_prompt.md clearly require HUMANOD_API_KEY — an incoherence that should be resolved before trusting the skill. No unrelated secrets are requested.
持久
The skill is not always-enabled and doesn't request elevated platform privileges. It does instruct the agent how to behave but does not request persistent presence or modify other skills.
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Humanod」。简介：Give your AI agent hands in the real world. Hire verified humans for physical t…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/armandobrazil/humanod/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
slug: humanod
display_name: Humanod
version: 1.0.0
tags: hiring, physical-tasks, api, gig-economy, real-world
description: Give your AI agent hands in the real world. Hire verified humans for physical tasks, data collection, and physical verification via the Humanod network.
credentials:
- HUMANOD_API_KEY
---
# 🦾 Humanod: The Physical API for AI Agents
**Humanod** bridges the gap between the digital and physical worlds. It allows AI agents to seamlessly hire real, verified humans to perform tasks in the real world, such as taking photos of a specific location, verifying if a store is open, or performing local data collection.
## 🔑 Authentication
To use this skill, you must provide your `HUMANOD_API_KEY`.
1. Create an account at [Humanod.app](https://www.humanod.app)
2. Navigate to your Developer Dashboard.
3. Generate a new API Key (it should start with `hod_...`).
## 🛠️ How it Works
1. **Create a Task:** Use the `createTask` tool to broadcast a mission to the Humanod network. You define the budget, location, and validation criteria.
2. **Escrow & Dispatch:** Funds are securely held in escrow. Human workers in the target location receive a notification and can accept the task.
3. **Execution & Proof:** The human worker performs the task and uploads proof (e.g., photos, text completion).
4. **Validation:** Review the submitted proof and use `validateSubmission` to approve the work and release payment, or request revisions/reject.
## 🧰 Available Tools
| Tool | Description |
|---|---|
| `createTask` | Broadcast a new physical or digital task to the Humanod network. Requires title, description, price, and deliverables. |
| `listTasks` | Retrieve all tasks created by your agent to monitor their overall status. |
| `getTaskStatus` | Check the current status of a specific task (Open, In Progress, Completed). |
| `getTaskApplications` | Review the human workers who applied to your task and their submitted proofs. |
| `acceptApplication` | Assign the task to a specific human applicant. |
| `validateSubmission` | Approve (release funds) or reject (request revision) the submitted proof from the worker. |
| `cancelTask` | Cancel an open task and refund the escrowed budget back to your wallet. |
| `getWalletBalance` | Check your available funds in EUR. |
## 💡 Example Usage Scenarios
### Scenario 1: Physical World Verification
An agent needs to know if a specific coffee shop is currently open because Google Maps is outdated.
> *Agent Action:* Calls `createTask` with a €5 budget, setting `location_name: "123 Main St"`, asking for a photo of the storefront showing whether the "Open" sign is lit.
### Scenario 2: Geographically Distributed Data Collection
An agent needs photos of 10 different real estate properties across a city for a market analysis report.
> *Agent Action:* Calls `createTask` repeatedly for each location, setting `category: "photography"` and defining strict `validation_criteria` (e.g., "Must be a clear, daytime photo of the front facade").
---
*For support or to learn more about advanced integrations (LangChain, CrewAI), visit [docs.humanod.app](https://docs.humanod.app).*