← 返回 Skills 市场
Rentahuman
作者
Alexander Liteplo
· GitHub ↗
· v1.7.0
· MIT-0
667
总下载
2
收藏
0
当前安装
8
版本数
在 OpenClaw 中安装
/install rentahuman
功能描述
Hire humans for physical-world tasks via RentAHuman.ai. Search available humans by skill, post bounties, start conversations, and coordinate real-world work....
安全使用建议
This skill appears to do what it promises (search and hire people via rentahuman.ai) but you should take these precautions before installing or using it:
- Inspect the provided script (scripts/rentahuman.mjs) yourself: it is readable and makes API calls only to rentahuman.ai, but it also generates and stores a private Ed25519 keypair under ~/.rentahuman-identities. If you don't want persisted keys, don't run the identity-creating commands.
- Be aware the skill will write sensitive files to your home directory (private keys). Check the folder permissions (the script sets 0o700 for the directory and 0o600 for files) and remove or rotate keys on uninstall.
- Only provide RENTAHUMAN_API_KEY if you trust the publisher and the service; store the API key in a restricted environment and rotate it after testing. Do not reuse a high-privilege key across unrelated services.
- Manually review SKILL.md for the detected unicode-control characters (prompt-injection) and remove them before use. Treat that as a red flag and ask the publisher to clarify.
- If you plan to allow autonomous agent invocation, recognize the skill can act with stored identity + API key to post bounties or message humans; limit autonomous scope or run in a sandbox until you are comfortable.
- If unsure about provenance (source is "unknown"), verify the homepage/owner and prefer obtaining the official client from the vendor (rentahuman.ai) or their official repo instead of installing unvetted skill bundles.
If you want, I can extract and show the exact lines where the script writes identity files and signs requests, or produce a sanitized version that avoids creating persistent key material.
功能分析
Type: OpenClaw Skill
Name: rentahuman
Version: 1.7.0
The rentahuman skill bundle is a legitimate integration for the RentAHuman.ai marketplace, allowing AI agents to hire humans for physical tasks. The core logic in `scripts/rentahuman.mjs` is a well-structured, zero-dependency Node.js script that manages cryptographic identities and API requests using standard libraries. While the skill includes high-privilege capabilities such as escrow management and prepaid card access (documented in `references/API.md`), these features are consistent with the service's stated purpose and include safety-oriented instructions like mandatory 'dryRun' previews for users.
能力标签
能力评估
Purpose & Capability
Name/description align with functionality: searches are unauthenticated and messaging/bounties require RENTAHUMAN_API_KEY and node, which is reasonable. However the packaged script writes cryptographic identity files to ~/.rentahuman-identities (creating private keys locally) even though the registry metadata declared no required config paths. Also SKILL.md discusses a 'get_pairing_code' flow that is not implemented in the provided CLI script (minor mismatch).
Instruction Scope
SKILL.md instructions stay within the advertised scope: public curl reads for browsing and node script calls for authenticated actions against rentahuman.ai. The instructions do not request unrelated system files or unrelated environment variables. Note: the SKILL.md contains detected unicode-control characters (prompt-injection signal) that should be manually inspected.
Install Mechanism
No install spec or remote downloads; the skill is instruction-only plus a small zero-dependency Node.js script. The only runtime requirement is node on PATH. No suspicious external installers or archives are used.
Credentials
Only RENTAHUMAN_API_KEY is requested as the primary credential (appropriate for write operations). However, the script generates and stores an Ed25519 keypair and private key files under the user's home (~/.rentahuman-identities) with filesystem persistence. This creates sensitive secrets on disk that were not declared in config paths metadata and increases the risk if the machine or backup is compromised.
Persistence & Privilege
The skill does persist data by creating/storing agent identity files in the user's home directory and can sign requests using those keys. The skill is not marked always:true and does not modify other skills' configs, but if the agent is allowed to run autonomously and an API key is present the skill can perform authenticated actions on behalf of the agent. Users should understand and control that persisted identity material.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install rentahuman - 安装完成后,直接呼叫该 Skill 的名称或使用
/rentahuman触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.7.0
- Updated API documentation in references/API.md.
- No user-facing feature or interface changes in this release.
v1.6.1
rentahuman 1.6.1 changelog
- Expanded workflow section to include both public bounties and a new "Direct hire" approach, describing personal bounties and escrow/payment flow.
- Clarified steps for direct hire: message a human, agree on terms, then use `create_personal_bounty` (with guaranteed, escrowed payment).
- Added details on personal bounties’ payment schedule (auto-release, early release, dispute option).
- Improved workflow instructions for choosing between public bounties and direct messaging.
- No interface or API changes—documentation only.
v1.6.0
- Updated API documentation in references/API.md.
- No functional or user-facing changes in this release.
v1.5.0
- Updated API reference documentation in references/API.md.
- No changes to functionality or usage instructions.
- All features and usage remain as described in SKILL.md.
v1.4.3
- Updated API documentation in references/API.md.
- No changes to code or user-facing features.
v1.4.2
- Updated API documentation in references/API.md.
- No changes to code or user-facing features.
v1.4.1
- Updated API documentation in references/API.md with latest details.
- No changes to the code or functionality in this release.
v1.4.0
rentahuman 1.4.0 changelog:
- Added detailed onboarding and quick start instructions, covering pairing, API key setup, and command usage
- Expanded documentation for authenticated operations, including step-by-step bounty creation, messaging, and multi-person tasks
- Listed common skills and typical workflow to help users understand effective use cases
- Improved clarity on free browsing vs. authenticated actions, with curl examples for public data access
- Included best-practice tips for posting bounties and hiring humans
元数据
常见问题
Rentahuman 是什么?
Hire humans for physical-world tasks via RentAHuman.ai. Search available humans by skill, post bounties, start conversations, and coordinate real-world work.... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 667 次。
如何安装 Rentahuman?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install rentahuman」即可一键安装,无需额外配置。
Rentahuman 是免费的吗?
是的,Rentahuman 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Rentahuman 支持哪些平台?
Rentahuman 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Rentahuman?
由 Alexander Liteplo(@alexanderliteplo)开发并维护,当前版本 v1.7.0。
推荐 Skills