Back to skill

Security audit

00 Overview

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Chinese parenting assistant concept, but it plans long-term child development records, family/social sharing, peer comparison, and retention/lock-in without clear privacy, consent, deletion, or sharing controls.

Review carefully before installing or publishing. The package is not executing code, but it should add clear controls for minors' data: parental consent, data minimization, optional recordkeeping, secure storage, explicit family-sharing permissions, export and deletion, retention limits, and warnings that developmental comparisons are informational rather than medical diagnosis.

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
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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly promotes maintaining a 3-year child growth archive, sharing it with family, and comparing a child against peers, but provides no privacy, consent, retention, or protection guidance. Because this concerns minors' longitudinal developmental data, the omission increases the risk of over-collection, unauthorized sharing, and unsafe handling of sensitive personal information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The entire skill description is written in Chinese and presents the assistant as a Chinese-language parenting tool, but it does not state that this is a China-specific or Chinese-only skill nor offer any user language choice. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.