Yutori research

PassAudited by ClawScan on May 10, 2026.

Overview

This is a straightforward Yutori web-research integration, but it uses your Yutori API key and sends research or browsing tasks to Yutori's cloud service.

Use this skill if you are comfortable sending the requested research or browsing task to Yutori. Provide a limited-scope Yutori API key, verify YUTORI_API_BASE points to the intended Yutori dev or production endpoint, avoid confidential prompts unless approved, and require confirmation before any browsing task submits forms or changes website/account state.

Findings (4)

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

The skill can spend or access whatever your Yutori API key permits for Research/Browsing tasks.

Why it was flagged

The runner uses a Yutori API key from the environment or OpenClaw config and sends it as an authentication header. This is purpose-aligned, but it uses account/API authority.

Skill content
const API_KEY = process.env.YUTORI_API_KEY ?? loadKeyFromOpenClawConfig(); ... "x-api-key": API_KEY
Recommendation

Use a Yutori key with only the needed permissions and confirm YUTORI_API_BASE is set to the intended dev or production Yutori endpoint.

What this means

Sensitive research prompts, URLs, or extracted content may be processed by Yutori's cloud service.

Why it was flagged

Research prompts plus timezone/location context are sent to a cloud API endpoint. This is expected for a cloud research service, but it means task contents leave the local agent.

Skill content
const API_BASE = process.env.YUTORI_API_BASE ?? "https://api.dev.yutori.com"; ... body: JSON.stringify({ query, user_timezone, user_location })
Recommendation

Do not include confidential data unless you are comfortable sending it to Yutori, and set the production endpoint if you do not intend to use the default dev endpoint.

What this means

A poorly specified browsing task could interact with websites in ways the user did not intend.

Why it was flagged

The skill can delegate web navigation and form interaction to a cloud browser. This fits the stated browsing purpose, but website actions should remain explicitly user-requested.

Skill content
Use the Browsing API when the user asks: ... “Fill a form / click through pages / collect items”
Recommendation

Give narrow browsing instructions and require confirmation before submitting forms, posting content, purchasing, logging in, or changing account data.

What this means

Install-time metadata may not warn that the skill needs a Yutori API key.

Why it was flagged

The registry metadata does not advertise the Yutori API key requirement even though SKILL.md and the script disclose and require it. This is an under-declaration, not hidden behavior.

Skill content
Required env vars: none ... Env var declarations: none ... Primary credential: none
Recommendation

Treat this skill as requiring YUTORI_API_KEY and optionally YUTORI_API_BASE despite the metadata omission.