Daily Planner

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.

What this means

Personal commitments, names, deadlines, and context from conversations may be saved and reused in later planning sessions.

Why it was flagged

The skill is designed to extract commitments from conversations and store them for future reminders and planning, creating persistent memory of personal or work obligations.

Skill content
Every promise or commitment made in conversation
Recommendation

Review the ~/planner/ files periodically, avoid logging highly sensitive commitments unless needed, and delete or archive stored data when it is no longer useful.

What this means

If connected to calendar or email tools, the agent could read scheduling and message metadata relevant to planning.

Why it was flagged

The skill may rely on delegated access to calendar and email data if those integrations are available, which is expected for a planner but involves sensitive account information.

Skill content
Input sources:
- Calendar events for today
- Open commitments from `commitments.md`
- Pending tasks from previous day
- Emails flagged as "needs decision" (if email access)
Recommendation

Grant only the minimum calendar/email permissions needed, and confirm which accounts and folders the agent may use.

What this means

The planner may add calendar blocks or, where integrations exist, affect notifications or auto-replies as part of protecting focus time.

Why it was flagged

The calendar workflow allows automatic creation of deep-work blocks when time is available; this is aligned with the skill purpose but can mutate a user’s calendar.

Skill content
If open: block automatically
Recommendation

Require confirmation before externally visible changes such as creating calendar events, rescheduling meetings, sending summaries, or enabling auto-replies.