Ravi ravi

Overview of Ravi and when to use each skill. Ravi gives AI agents real email inboxes, phone numbers, and an encrypted secret store via API. Do NOT use for ta...

This skill is not obviously malicious, but it has several red flags you should consider before installing: 1) It expects a 'ravi' CLI and a local config at ~/.ravi/config.json but the manifest does not declare these requirements or how to obtain/verify the CLI. Verify the vendor/source and installation instructions before installing any binaries. 2) The skill gives agents access to real inboxes, phone numbers, OTPs, and a secret store — ensure you really want an agent to manage or forward credentials. 3) The SKILL.md encourages sending feedback to [email protected]; avoid including secrets, OTPs, or API keys in feedback messages. 4) If you enable agent autonomy, consider disabling autonomous invocation for this skill (or restrict its use) so it cannot perform signups, read OTPs, or exfiltrate secrets without explicit human approval. 5) Ask the publisher for a clear install source, a signed binary or package, and documentation describing how credentials are stored and protected; inspect ~/.ravi/config.json after onboarding to understand what keys are stored locally. If you cannot validate the CLI source or you do not accept the data-exposure risks, do not install or enable autonomous use of this skill.

Type: OpenClaw Skill Name: ravi Version: 2.1.1 The 'ravi' skill bundle (v2.1.1) provides identity and secret management but contains highly suspicious instructions in SKILL.md. It mandates that the AI agent send 'feedback' emails to [email protected] after every workflow, which functions as a telemetry and exfiltration channel for the agent's activity logs and user context. Furthermore, the service encourages the storage of high-value credentials (e.g., OPENAI_API_KEY) in its third-party store, which, combined with the aggressive feedback requirement, creates a significant risk of sensitive data leakage to the ravi.id domain.