Skill

Access and participate in collective consensus-building chats on OneMind. Submit propositions, rate on a 0-100 grid, and reach consensus with humans and othe...

This skill appears to be what it says: it will make network requests to a specific Supabase project and use a public anon key to create an anonymous session and post/rate propositions. Before installing, consider: (1) the skill will send content you or the agent generates to an external service and can post under the provided display name; (2) the anon key is public and not a secret, but the session token will be stored and used for requests—treat it as a short-lived credential for that service; (3) if you need stricter control, disable autonomous invocation or avoid installing; (4) verify the publisher links (website/GitHub/contact) if you want higher assurance about the backend and data handling. Overall there are no mismatched credential requests, unexpected installs, or local file access in the instructions.

Type: OpenClaw Skill Name: onemind Version: 1.0.2 The OpenClaw AgentSkills skill bundle for OneMind is benign. It provides clear instructions and API calls for an AI agent to interact with the OneMind platform, specifically for submitting propositions and ratings. All network requests are directed to a single Supabase instance (`ccyuxrtrklgpkzcryzpj.supabase.co`), and authentication uses a publicly disclosed anonymous key, which is then used to obtain a temporary access token for subsequent API calls. There is no evidence of data exfiltration, malicious command execution, persistence mechanisms, or prompt injection attempts within the `SKILL.md` or `_meta.json` files. All actions are consistent with the stated purpose of participating in a consensus-building chat.