Back to skill

Security audit

Kindergarten Assistant

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent as an early-childhood teaching assistant, but it encourages persistent plaintext records about very young children and families without privacy safeguards.

Install only if you will use it with sanitized or pseudonymous notes, avoid storing photos, names, contact details, medical/safeguarding details, or private family communications in the workspace, and keep any required real child records in an approved secure childcare-record system with consent, access control, retention, and deletion procedures.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
MEMORY.md:11
Finding

Plaintext Persistence of Sensitive Information About Children and Families

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly says it maintains a memory file containing child profiles, developmental progress, observations, parental communication, and related notes. In the context of infants and toddlers, this is highly sensitive personal and developmental data, and the skill provides no minimization, consent, retention, or access-control guidance, creating a real privacy and exposure risk if the memory is persisted or surfaced to unintended parties.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The persistent memory behavior creates a natural-language data retention risk because the skill encourages ongoing storage of sensitive child and family information over time. Even without overt exfiltration logic, retaining identifiable observations and parent communications increases the chance of accidental disclosure, over-collection, and reuse outside the original educational purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.