Tempest Weather

PassAudited by ClawScan on May 1, 2026.

Overview

This is a coherent WeatherFlow Tempest weather integration, but users should note it uses a personal API token and may return station metadata such as exact coordinates.

Before installing, confirm you are comfortable giving the agent access to your Tempest token and station ID. The skill appears purpose-aligned and non-destructive, but its output may include exact station location metadata; remove those fields if you do not want them exposed in conversations.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If installed and configured, the agent can use the Tempest token to read the configured station's live observations and related station data.

Why it was flagged

The script uses the user's Tempest personal access token to query the WeatherFlow API. This is expected for the skill's purpose and is not hardcoded, but it is still account-linked authority.

Skill content
parser.add_argument("--token", default=os.environ.get("TEMPEST_TOKEN"), help="API token") ... resp = requests.get(url, params={"token": token}, timeout=10)
Recommendation

Use a token intended for this integration, keep it out of shared logs or prompts, and revoke it from Tempest if you stop using the skill.

What this means

Weather responses may expose the physical location of the configured station to the agent conversation or anyone who can see the output.

Why it was flagged

The normalized output includes exact station location metadata. This comes from the Tempest API and is purpose-adjacent, but it may reveal a home or device location.

Skill content
"latitude": data.get("latitude"),
        "longitude": data.get("longitude"),
        "timezone": data.get("timezone"),
        "elevation_m": data.get("elevation")
Recommendation

Only use this skill in contexts where returning station location metadata is acceptable, or modify the script to omit latitude and longitude if you only need weather readings.

What this means

If the user installs dependencies manually, they rely on the current package available from their Python package index.

Why it was flagged

The setup guidance references installing an unpinned Python dependency. This is not automatic and is normal for a Python-based API client, but it depends on the user's package source.

Skill content
- `curl` or `requests` (`pip install requests`)
Recommendation

Install dependencies from a trusted environment and consider pinning a known-good `requests` version if you manage this skill in a reproducible setup.