Baby Guide

Security checks across malware telemetry and agentic risk

Overview

This baby-care skill is mostly local, but it includes under-disclosed pediatric emergency treatment guidance and an unrelated helper script that stores command history.

Install only after reviewing the medical and persistence behavior. Treat all emergency and medication output as general reference, not medical advice, and use professional care for urgent symptoms. Consider removing or avoiding scripts/script.sh unless you want a design helper that writes local command history.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (3)

Context-Inappropriate Capability

Medium

Confidence: 96% confidence
Finding: The script includes detailed pediatric emergency triage, medication thresholds, dosing conditions, and escalation guidance, but there is no manifest context establishing medical authority, intended clinical scope, or human review. In a general-purpose agent skill, this can cause users to rely on unverified medical instructions for urgent child-health decisions, creating a meaningful risk of delayed care or inappropriate treatment.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The emergency section gives actionable medical instructions, including drug-use criteria and urgent-care decision points, without an upfront warning that the content is not medical advice and may not fit the child's age, history, or local standards. Because this is pediatric emergency content, users may over-trust it in time-sensitive situations, increasing the chance of harm from self-treatment or delayed professional care.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The script logs command arguments to a persistent history file under the user's data directory without notifying the user or obtaining consent. Even though this tool appears to be a benign design helper, arguments may still contain sensitive project names, internal URLs, notes, or other private data, creating an avoidable local privacy leak if the filesystem is accessed by other users, backups, or support tooling.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal