ai-high-quality-briefing
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
Private or account-only page content could be summarized into a briefing or publishable copy if the agent uses an authenticated browser page.
This allows the agent to rely on an authenticated browser session or already-open account pages, but the skill does not bound which accounts/pages may be used or require explicit confirmation before including that content in a briefing.
optionally use browser snapshot on already-open or login-required pages
Only allow browser snapshots for pages you explicitly choose, and avoid using logged-in/private pages unless you are comfortable with their contents appearing in the generated output.
The agent may keep generating scheduled briefings until the reminder or cron entry is changed or removed.
The skill supports recurring reminder-style execution, which is purpose-aligned when requested but creates persistent future activity.
When the user wants recurring briefings: - use `cron`
Confirm the schedule, topic scope, and how to stop or edit the recurring briefing before enabling it.
The skill may fail to find its references or read from an unexpected local path if that path exists in the environment.
The skill points to reference files using a hardcoded absolute path tied to a specific local user directory rather than a portable relative skill path.
Read `/Users/youke/.openclaw/workspace/skills/ai-high-quality-briefing/references-query-patterns.md`
Prefer packaged relative paths for the reference files and verify the installed files match the reviewed artifacts.