4To1 Planner - AI Planning Coach

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent planning helper that uses expected planning-service access, with user-visible cautions around API tokens, local stored plans, and shell setup scripts.

Before installing, decide which backend you trust for your planning data. If using Notion or Todoist, create a dedicated/scoped integration where possible and keep ~/.config/4to1/config private. Avoid the Google Calendar setup path until the missing helper script is provided.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

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.

#
ASI03: Identity and Privilege Abuse
Low
What this means

The tokens can give the skill access to your planning data in those services, depending on the token or integration scope.

Why it was flagged

The setup flow asks for third-party API tokens and stores them in a local config file so the planner can access Notion or Todoist.

Skill content
read -p "Paste your Notion API key: " notion_key ... echo "NOTION_API_KEY=$notion_key" >> "$CONFIG_DIR/config"
Recommendation

Use a dedicated Notion integration shared only with the intended parent page, use the least-privileged Todoist token available, and revoke tokens if you stop using the skill.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

Running these commands will modify the connected planning workspace by creating planner pages and databases.

Why it was flagged

The skill documents API calls that create pages and databases in the user's Notion workspace.

Skill content
curl -s -X POST "https://api.notion.com/v1/pages" ... curl -s -X POST "https://api.notion.com/v1/databases"
Recommendation

Only allow the agent to run setup or write commands after you choose the backend and confirm the target workspace or project.

#
ASI05: Unexpected Code Execution
Low
What this means

If the local config file were manually edited or tampered with, running the status script could execute unexpected shell commands.

Why it was flagged

The status script loads the config file as shell code rather than parsing it as simple key-value data.

Skill content
source "$CONFIG"
Recommendation

Keep ~/.config/4to1/config private and trusted; maintainers should parse config values safely and set restrictive file permissions.

#
ASI06: Memory and Context Poisoning
Low
What this means

Your goals, tasks, reviews, and habits may be stored and reused as context for future planning conversations.

Why it was flagged

Weekly reviews intentionally read and reuse stored planning state, reflections, and personal productivity lists.

Skill content
From the configured backend, pull: Current 2-week sprint tasks and completion status ... Last review ... Not-To-Do list + Time Wasters list
Recommendation

Use the local Markdown backend if you want offline storage, and review what you store in connected services before letting the agent read or update it.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

The Google Calendar option may not work as documented, and its OAuth behavior is not reviewable from the provided artifacts.

Why it was flagged

The Google Calendar setup path references gcal_setup.py, but that helper is not included in the provided file manifest.

Skill content
echo "   python3 $(dirname $0)/gcal_setup.py"
Recommendation

Do not use the Google Calendar option until the missing helper script is supplied and reviewed.