RingBot

Make outbound AI phone calls. Use when asked to call a business, make a phone call, order food by phone, schedule appointments, or any task requiring voice calls. Triggers on "call", "phone", "dial", "ring", "order pizza", "make reservation", "schedule appointment".

This skill describes a plausible telephony workflow but is packaged only as instructions — no code or install is included — and the registry metadata fails to declare the sensitive credentials the SKILL.md says are required. Before installing or using it: (1) Understand you will need to supply Twilio credentials (and possibly LiveKit/Groq keys) if you run the DIY stack; those are sensitive and allow call-making and billing charges. (2) If you use the hosted option, be careful about giving your Twilio auth token to a third party — prefer OAuth or a vetted integration. (3) The skill expects local services (python agent and API) and a 'goplaces' CLI that are not included; obtain those components from trusted, verifiable sources before running. (4) Consider privacy and legal risks (call recording, consent, PII collection) and minimize what context/credentials you share. (5) If you want to proceed, ask the publisher for: declared required env vars in registry metadata, a link to source code or official repository, and details on the hosted service's security/practices. If the publisher cannot provide verifiable provenance, treat it with caution.

Type: OpenClaw Skill Name: ringbot Version: 1.1.0 The skill bundle describes an AI phone call agent that uses local services and external APIs (Twilio, LiveKit, Groq). The `SKILL.md` provides instructions for setup and usage, including `curl` commands to a local endpoint and `goplaces` commands to find phone numbers. While the skill requires sensitive API keys for its operation and involves shell/network access, these capabilities are directly aligned with its stated purpose of making outbound phone calls. There is no evidence of intentional harmful behavior such as data exfiltration, malicious execution, persistence, or prompt injection attempting to subvert the agent's behavior for unauthorized actions.