rentahuman.ai

Hire humans for physical-world tasks via RentAHuman.ai. Search available humans by skill, post bounties, start conversations, and coordinate real-world work....

This skill appears to be a coherent client for rentahuman.ai, but take these precautions before installing or using it: 1) Verify the source/owner if possible — the registry owner is unknown. 2) Treat RENTAHUMAN_API_KEY like a secret: use a dedicated API key with the minimum necessary privileges and rotate/revoke it if compromised. 3) Be aware the skill creates ~/.rentahuman-identities and stores a private key there (0600). If you do not want persistent local credentials, avoid running authenticated commands. 4) Inspect SKILL.md for hidden/zero-width/unicode control characters (scanner flagged them) and review the included script; run it in a sandbox or isolated environment first if you have doubts. 5) If you will use payment/escrow endpoints, ensure the account and API key policies are appropriate, and monitor for unexpected transactions. If anything looks unfamiliar or you cannot verify the publisher, prefer read-only usage via curl and avoid providing the API key.

Type: OpenClaw Skill Name: rent-a-human Version: 1.0.0 The OpenClaw AgentSkills bundle for RentAHuman.ai is classified as benign. The `scripts/rentahuman.mjs` script uses standard Node.js modules, securely manages agent identities in `~/.rentahuman-identities` with appropriate file permissions (0o700 for directory, 0o600 for files), and communicates exclusively with the `https://rentahuman.ai/api` endpoint via HTTPS. It requires an API key for write operations, which is handled via an environment variable. The `SKILL.md` documentation provides clear, functional instructions for the AI agent without any evidence of prompt injection attempts or directives for malicious behavior. There are no external dependencies, obfuscation, or attempts at data exfiltration, persistence, or unauthorized execution.