安全打卡提醒

• Outcome: Review
• Latest audit: May 27, 2026 at 10:33 PM UTC
• Version:
  1.2.0

Overview

This safety check-in skill is understandable, but it sets up ongoing automation and can automatically contact someone without enough user control or safeguards.

Review carefully before installing. Confirm exactly how Feishu messages and phone calls will be sent, who is allowed to check in, how to stop or delete the scheduled tasks, how stored emergency contact data is protected and removed, and whether the emergency contact has consented to automated calls.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The README describes automatic saving of configuration, scheduled monitoring, reminder delivery, check-in tracking, and automatic emergency contact calls, but it does not clearly warn users about persistent storage of personal data or the real-world consequences of missed check-ins. Because the skill handles sensitive contact information and can trigger outbound contact actions without an explicit warning in the user-facing description, users may enable it without informed consent, creating privacy and safety risks.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The skill uses broad activation keywords such as “打卡”, which are common in normal conversation and can cause unintended invocation. In this skill, accidental activation is more dangerous than usual because activation can lead into collecting sensitive contact data and configuring persistent automation.

Missing User Warnings

High

• Confidence: 96% confidence
• Finding: The skill performs persistent and potentially high-impact actions automatically: saving personal data, creating scheduled tasks, monitoring user activity, and calling an emergency contact after 7 missed days. Without explicit risk disclosure and affirmative consent, users may not understand that enabling the skill causes ongoing monitoring and outbound contact, which can create privacy, safety, and false-emergency risks.

VirusTotal

66/66 vendors flagged this skill as clean.