Security audit

Baby (Tracker, Feeding, Sleep, Triage, Visit Prep)

Security checks for vulnerabilities and agentic risk

Overview

This baby tracker saves sensitive baby-care notes locally only after confirmation and does not run code or send data out.

Before installing, be aware this skill can create local notes containing sensitive child health and caregiver information in ~/baby/. Use it only on a device/account you trust, keep only details that help care coordination, and review or delete those files when you no longer need them.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This template encourages storing highly sensitive information about an infant and caregivers locally, including birth date, care team, medical context, symptoms, and emergency preferences, but provides no privacy warning, minimization guidance, or retention controls. In a baby-care context, that omission is more serious because the data involves a child and can expose medical, household, and caregiver details if the device, account, or filesystem is shared or compromised.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation guidance is intentionally broad and encourages triggering on many baby-related topics without a clear boundary for incidental mentions. In a caregiver context, that can cause over-activation, unwanted persistence, and collection or surfacing of sensitive child-health context when the user did not intend to engage this skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The template directs users to update a persistent 'handoff and memory' after a pediatric visit, which can encourage storage of sensitive infant health information without any minimization, consent, retention, or privacy guidance. In a baby-tracking skill, this increases the chance that medical details, medication history, and symptom timelines are retained or shared more broadly than the caregiver expects.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: This markdown file presents a general-purpose 'Memory Template - Baby' skill artifact but does not specify when it should be used, what user requests should activate it, or any exclusion conditions. For markdown skill content, the absence of clear trigger boundaries can lead to over-broad application in ordinary baby-care conversations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill instructs the agent to store baby-care and health-related information internally, including symptoms, medications, caregiver setup, and alert preferences, without requiring explicit informed consent first. Because this concerns infant and family health context, undisclosed retention creates privacy and expectation risks and could lead to sensitive profiling beyond what the user realizes is being saved.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.