Security audit

Plan Tracker

Security checks for vulnerabilities and agentic risk

Overview

This package is a coherent plan-tracking and reminder skill, with notable but disclosed background reminder and notification behavior.

Before installing, understand that full functionality requires a separate Python wheel and setup command that can register an MCP server and start a persistent reminder daemon. Use email notifications only if you are comfortable sending reminder content and recipient details through the configured email service.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly supports email sending through a third-party REST API but does not require a clear user-facing disclosure that plan content, reminder metadata, and recipient information may be transmitted off-platform. This creates a privacy and consent risk because users may share sensitive personal goals, schedules, or notes without understanding that external service processing is involved.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The skill's natural-language workflow examples and user-facing prompts are presented in Chinese, which can imply a fixed language behavior. There is no accompanying statement that the assistant should match the user's preferred language or that the skill is intentionally limited to Chinese for a documented reason.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The workflow states that after 10 minutes of no response, the system auto-marks the day's plan as incomplete, but the skill does not clearly warn users about this automatic status change at configuration time or before activation. This can misrepresent user activity, affect downstream analysis, and erode trust if reminders drive progress metrics or recommendations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.