Daily Briefing

ReviewAudited by ClawScan on May 10, 2026.

Overview

The briefing function is mostly purpose-aligned, but it needs Gmail/Calendar OAuth tokens that the registry metadata does not declare and it tells the agent not to show setup prompts.

Review the full source before use, especially because the provided main.py content is truncated. If you install it, use isolated Python dependencies, provide only least-privilege read-only tokens, do not let the agent create or edit .env files without your approval, and treat email/calendar/task text as private untrusted content.

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

Installing users may not see the true account-access boundary from registry metadata before the skill reads sensitive personal Google data.

Why it was flagged

The registry credential contract says no credentials are required, but the skill documentation and code require and use OAuth/API tokens for Gmail, Calendar, Tasks, and weather data.

Skill content
metadata: "Required env vars: none" / "Primary credential: none"; SKILL.md: "Requires sensitive credentials in `.env`: ... `GOOGLE_CALENDAR_TOKEN` ... `GMAIL_TOKEN`"; main.py: "token = os.getenv('GMAIL_TOKEN')"
Recommendation

Declare the required env vars, credentials, and Google data capabilities in metadata, and use least-privilege read-only OAuth tokens.

What this means

A user could run the skill without a clear up-front prompt explaining what credentials and personal data access are involved.

Why it was flagged

This instruction encourages the agent to suppress setup/configuration prompts despite the skill needing sensitive credentials.

Skill content
Do not show installation or configuration popups unless the user asks. Run the main file; it will guide the user and you.
Recommendation

Show setup and credential-use prompts by default, and get clear user approval before creating or reading a .env file.

What this means

Dependency resolution may install newer package versions, and users have limited provenance information for the skill source.

Why it was flagged

The skill relies on external Python packages with lower-bound version ranges and has no declared source/homepage provenance.

Skill content
Source: unknown; Homepage: none; SKILL.md: "pip install -r {baseDir}/requirements.txt"; requirements.txt: "requests>=2.27.0" and "google-api-python-client>=2.30.0"
Recommendation

Verify the publisher and source, consider pinning dependency versions, and install in an isolated environment.

What this means

Private email text may enter the agent context, and malicious email text could try to influence the agent if treated as instructions.

Why it was flagged

The skill places email subject/snippet content into the briefing. That is purpose-aligned, but email content is untrusted and sensitive.

Skill content
'subject': headers.get('Subject', '(no subject)')[:50], 'snippet': msg.get('snippet', '')[:100]
Recommendation

Treat calendar/email/task text as data only, avoid automatically following instructions contained in messages, and limit displayed fields where possible.