Back to skill

Security audit

儿童成长跟踪与评估

Security checks across malware telemetry and agentic risk

Overview

This is a local child-growth recordkeeping skill with disclosed sensitive persistence, but users should control when it writes child-related observations.

Install only if you are comfortable storing a child’s development, school, emotional, and family-observation notes in workspace files that may be synced or backed up. Consider narrowing broad triggers and asking the agent to confirm before creating or updating records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes broad everyday terms such as '关系' and '情绪' and says the skill 'must trigger' when they appear. This can cause accidental activation in unrelated conversations, leading the agent to collect or write sensitive child-development information without clear user intent. Because the skill persists records to workspace files, over-triggering increases privacy and data-integrity risk.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill is designed to continuously record sensitive child behavioral, emotional, academic, and relational data into workspace files, but it does not clearly notify the user at the point of collection or obtain consent before persistence. This creates a real privacy risk, especially because the data concerns a minor and includes potentially sensitive psychological inferences that may be retained long term.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.