Security audit

Daily Planner

Security checks across malware telemetry and agentic risk

Overview

This daily planning skill is coherent and purpose-aligned, with a bounded but notable option or instruction to save a Markdown plan locally.

Before installing, be aware that the skill may create a daily Markdown plan in the current working directory and that the plan can include personal schedule or task details. Use it when you want structured planning help, and prefer confirming the output path before saving.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill documents a file-write action but does not declare any corresponding permission or capability boundary. This creates a mismatch between the apparent purpose of the skill and its effective behavior, reducing user visibility and enabling unintended persistence of user content in the working directory.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: A planning skill unexpectedly instructs the agent to save output to the user's working directory, which exceeds what many users would reasonably expect from a scheduling assistant. Even if the content is benign, unsolicited file creation can overwrite files, leave sensitive schedules on disk, or be abused as a persistence mechanism.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrases are broad, generic daily-planning requests that are likely to match ordinary conversation beyond narrowly scoped intent. In an agent environment, this can cause unintended skill activation, leading the planner to intercept user requests unexpectedly and influence outputs or workflow selection without clear user consent.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are broad enough to match common everyday planning language, so the skill may activate in many contexts where the user did not intend to invoke it. Over-broad activation becomes more dangerous here because the skill also includes persistence behavior, increasing the chance of unintended file creation or data handling.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The 'When to Use' section uses ambiguous examples that overlap with normal assistant behavior, making accidental activation more likely. In isolation this is lower impact, but in this skill it still matters because activation can lead to collecting personal schedule data and eventually writing a file.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill tells the agent to save a Markdown file in the user's working directory without warning the user or requesting permission. This is dangerous because it introduces a silent side effect, can persist potentially sensitive daily plans, and may create or overwrite files in an unexpected location.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.