ClawHub
Back to skill

Security audit

小学作业管理助手

Security checks for vulnerabilities and agentic risk

Overview

This homework helper is coherent and not malicious, but it handles children’s personal and schoolwork data without enough privacy, retention, or deletion guidance.

Review this before installing if it will be used with real children’s information. Prefer aliases instead of real names, avoid exact ages where possible, crop or redact homework photos, and do not upload faces, school names, class screenshots, contact details, or other identifiers unless you are comfortable sharing them with the chat platform and model provider. Check how your OpenClaw environment stores and deletes conversation memory or archived records.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly encourages sending teacher messages, homework details, and photos of children's schoolwork/images to chatbots and vision models, but provides no privacy notice, consent guidance, retention warning, or data-minimization advice. Because the skill is designed for young children and may process identifiable educational data, the omission increases the risk of exposing minors' personal information to third-party platforms or model providers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description and trigger phrases throughout the file assume Chinese-language interaction, but the skill does not state that this is an optional language preference or a justified region-specific limitation. This can violate language/locale policy when users are not given a choice or clear notice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs users to provide a child's name, grade, age, and preferences, which are personal data about a minor, but it gives no minimization, retention, or privacy warning. In a family/education context, collecting identifiable child data without clear safeguards increases the risk of unnecessary exposure, profiling, or accidental disclosure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill supports uploading photos and archiving children's mistakes, generating ongoing educational records that may contain handwritten work, names, school details, or other sensitive student information. Without any warning, consent guidance, or handling limits, this creates privacy risk for a minor and could expose sensitive educational data if retained or shared improperly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.