stand up reminder

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:29 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed stand-up reminder that creates recurring cron notifications, with no evidence of hidden code, credential access, exfiltration, or destructive behavior.

Install this if you want recurring stand-up reminders. After creating one, check the cron task name, task ID, timezone, language, interval, and enabled status so you can pause, edit, or delete it later; be aware that short generic requests may create a reminder using defaults.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger list includes generic everyday phrases such as '健康提醒' and 'stand up reminder', which can increase the chance of accidental or overly broad activation in normal conversation. In a skill that automatically creates persistent cron reminders, unintended activation can cause unwanted task creation and user annoyance, even if it does not directly create a severe security compromise.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation examples are broad natural-language phrases such as “提醒我每小时站起来活动” and related variants, which can plausibly appear in ordinary conversation rather than as a deliberate request to invoke a specific skill. That increases the risk of accidental triggering or overlap with other reminder/task-management skills, leading to unintended task creation or ambiguous routing.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger definition is broad and ends with an open-ended “等时触发”, which can cause the skill to activate on loosely related user requests. Because this skill creates persistent cron jobs automatically, over-triggering can lead to unintended task creation, notification spam, and user confusion without clear confirmation boundaries.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: Defaulting output to Chinese without explicit user preference can cause unintended language mismatch, which is a safety and usability issue when the skill sends autonomous reminder messages. In this context, the risk is lower than code-execution flaws, but it can still result in confusing notifications and accidental disclosure of user language assumptions on shared devices.

VirusTotal

64/64 vendors flagged this skill as clean.