UK Trains

Query UK National Rail live departure boards, arrivals, delays, and train services. Use when asked about train times, departures, arrivals, delays, platforms, or "when is the next train" for UK railways. Supports all GB stations via Darwin/Huxley2 API.

This skill appears to implement what it says (query UK train boards) but there are a few things to check before installing or enabling it: - Expect to provide a NATIONAL_RAIL_TOKEN (Darwin API token). The registry metadata currently omits this — verify the skill will not be run without your consent. Store the token in a scoped place (skill config) rather than a broadly-shared environment variable when possible. - The bash CLI relies on curl and jq; ensure those are available and trustworthy on the host. - The bash script allows overriding HUXLEY_URL via the HUXLEY_URL environment variable. Do not set HUXLEY_URL to an untrusted endpoint — an attacker-controlled endpoint could receive your token and data. Prefer the default Huxley/Darwin endpoints or the Python SOAP client which calls realtime.nationalrail.co.uk directly. - Review the scripts locally (they are provided) and test with a throwaway token first. If you need higher assurance, ask the publisher to update the registry metadata to declare required env vars (NATIONAL_RAIL_TOKEN) and required binaries (curl, jq) so the platform can surface them to users. Because of the mismatched metadata and the endpoint-override option, treat this as suspicious until those issues are clarified.

Type: OpenClaw Skill Name: uk-trains Version: 1.0.0 The skill bundle is benign. Both `scripts/trains.sh` and `scripts/trains.py` interact with legitimate National Rail API endpoints (`huxley2.azurewebsites.net` and `lite.realtime.nationalrail.co.uk`) to query train information, as stated in `SKILL.md`. The `NATIONAL_RAIL_TOKEN` is read from the environment and sent to these APIs, which is an expected and documented behavior for the skill's functionality. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or prompt injection attempts against the agent in `SKILL.md`.