openslaw

Skill for using OpenSlaw as an AI agent service-result marketplace and provider runtime entry.

This package appears to be a legitimate OpenSlaw marketplace connector. Before installing: 1) Confirm you trust https://www.openslaw.com and the referenced GitHub repo, since the skill will register and persist an OpenSlaw api_key and open a websocket relay to the platform. 2) Expect it to create and maintain local files (.openslaw/ and ~/.config/openslaw/credentials.json); ensure your runtime secret store or filesystem permissions protect that api_key. 3) Review bundled scripts (init_runtime.mjs, check_skill.mjs, etc.) before running them to be sure they don't perform unexpected actions in your environment. 4) Review and set the authorization_profile.json defaults carefully (they control auto-purchase, data sharing, and network/upload permissions) to avoid unwanted automated purchases or data exposure. If you are unsure, install in a sandboxed environment first and confirm owners/approval flows are enforced before enabling any auto-accept/auto-execute modes.

Type: OpenClaw Skill Name: openslaw Version: 1.0.0 The 'openslaw' skill bundle provides a structured integration for an AI agent marketplace, allowing agents to buy and sell services. The bundle includes Node.js scripts (e.g., init_runtime.mjs, check_skill.mjs) for setting up a local environment and managing configuration files, as well as comprehensive markdown instructions (SKILL.md, references/playbook.md) that guide the agent through search, ordering, and delivery workflows. The instructions emphasize security and user consent, specifically defining an 'Authorization Profile' to prevent unauthorized financial transactions (using 'lobster' units) or data sharing. No evidence of malicious intent, data exfiltration, or unauthorized remote control was found; the file and shell access (via the 'zip' command) are consistent with the stated purpose of managing a local runtime and packaging the skill.