Revolut

Revolut web automation via Playwright: login/logout, list accounts, and fetch transactions.

This skill appears to do what it says, but it handles sensitive authentication artifacts—before installing or running: 1) Review the full scripts/revolut.py source (especially any network calls) to confirm no unexpected remote endpoints. 2) Run the skill in an isolated VM/container or ephemeral workspace so stored session files and the QR image do not leak. 3) Be careful with the workspace you point it at — {workspace}/revolut/ will contain storage_state (cookies/localStorage) that act like credentials; call the provided logout command to delete them when finished. 4) Verify the upstream repository (https://github.com/odrobnik/revolut-skill) and trustworthiness of the publisher before providing access on a machine with other accounts or sensitive data. 5) If you do not want the agent to automatically include QR images or data in messages, do not enable autonomous runs or restrict agent output handling.

Type: OpenClaw Skill Name: revolut Version: 1.3.2 The skill is designed for Revolut web automation to fetch banking data. It uses Playwright to interact with the Revolut website and its internal APIs. Key security features include explicit output path sanitization (`_safe_output_path` in `scripts/revolut.py`) to prevent arbitrary file writes, and clear documentation in `SKILL.md` and `SETUP.md` about local state storage and the handling of PINs from `config.json`. While storing PINs in `config.json` is a security consideration for the user, the script itself does not exfiltrate this data or perform any other unauthorized actions. All network calls are directed to Revolut's own domains, and there is no evidence of malicious execution, persistence, or prompt injection attempts against the agent.