Security audit

Plan Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent plan-tracking and reminder tool, but users should understand that setup can register a persistent reminder daemon and optional external notifications.

Install only if you are comfortable with a local reminder daemon, OpenClaw MCP configuration changes, and reminder content being sent through any notification channels you enable. Avoid enabling email or external message delivery for sensitive plans unless you trust the provider and recipient configuration.

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill explicitly references email sending via a third-party REST API and allows reminder notifications over email, but it does not clearly warn users that plan content and reminder metadata may be transmitted to an external service. Because plans may contain sensitive personal goals, schedules, or health/fitness details, this creates a privacy and informed-consent risk rather than a purely functional issue.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: Multiple workflow examples instruct the agent to interact in Chinese, such as asking users Chinese confirmation and reminder questions, but the document does not state that the skill is China-specific or provide any language opt-in. This can violate language/locale policy by imposing a specific language on users without choice.

Static analysis

No suspicious patterns detected.