Morning Briefing Generator

ReviewAudited by ClawScan on May 10, 2026.

Overview

This instruction-only skill is coherent for making a morning briefing, but it asks users to connect sensitive accounts and optionally schedule automated delivery of private information.

Before installing or using this skill, decide which accounts you really want included, grant the narrowest permissions available, avoid putting secrets in TOOLS.md or HEARTBEAT.md, and only enable the cron/Telegram automation after confirming where the briefing will be sent.

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

Connecting these accounts may allow the agent or its tools to read sensitive email, calendar, task, and messaging information.

Why it was flagged

The skill expects access to calendar, email, and messaging credentials. This is purpose-aligned for a briefing generator, but those permissions can expose private personal or work data.

Skill content
- Google Calendar (OAuth)
- Gmail (OAuth)
...
- Verify bot token in .env
Recommendation

Use least-privilege OAuth scopes where possible, connect only accounts needed for the briefing, and revoke tokens if you stop using the skill.

What this means

Those preferences may be reused in future agent sessions and could reveal private account or health context to anyone with access to the files.

Why it was flagged

The skill suggests storing personal preferences, account identifiers, and health-related briefing rules in persistent agent configuration files.

Skill content
Add to `TOOLS.md` or `HEARTBEAT.md`:
...
- Calendar: work@company.com, personal@gmail.com
- Email Accounts: work@company.com, personal@gmail.com
- Additional: Include Oura Ring sleep score if below 70%
Recommendation

Do not store secrets in these files, keep the preferences minimal, and remove or update the entries when they are no longer needed.

What this means

Sensitive briefing contents could be delivered to the wrong chat, workspace, or provider account if the destination is misconfigured.

Why it was flagged

The briefing may be automatically sent through an external messaging provider and can contain private email, calendar, task, and health summaries.

Skill content
Create a cron job that runs every weekday at 7am.
Generate my morning briefing and send it via Telegram.
Recommendation

Confirm the exact delivery destination, avoid including highly sensitive fields unless needed, and test with non-sensitive output first.

What this means

A scheduled briefing could keep accessing accounts and sending private summaries even when you no longer expect it.

Why it was flagged

The skill documents a recurring scheduled workflow. It is disclosed and user-directed, but it can continue running after setup until disabled.

Skill content
### Automated Daily Briefing (Cron)
```
Create a cron job that runs every weekday at 7am.
Generate my morning briefing and send it via Telegram.
```
Recommendation

Set up cron only if you want recurring automation, document where the job is installed, and remove or disable it when no longer needed.