ClawHub
Back to skill

Security audit

市级教育课题申报Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language education proposal-writing skill with no executable code, but users should avoid placing identifiable student or teacher data into generated research materials.

Before installing or using this skill, treat it as a proposal-writing aid and avoid entering identifiable student or teacher information. Use anonymized or aggregate examples for surveys, homework samples, interviews, classroom records, grades, or performance outcomes unless you have proper authorization and storage controls.

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
  • 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
89% confidence
Finding

The skill explicitly supports collecting, analyzing, and generating educational artifacts involving students and teachers, such as surveys, interviews, homework samples, classroom practice records, and performance-related outputs, but provides no privacy warning, data-minimization guidance, or restrictions on including personally identifiable or sensitive educational data. In a school context, these materials can easily contain minors' data, teacher evaluations, and other regulated personal information, creating a realistic risk of privacy violations, over-collection, or unsafe downstream handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The package description is entirely in Chinese, which suggests the skill may be oriented to a single language without any explicit opt-in, fallback, or documented locale restriction. Under the policy, language-specific behavior should either offer user choice or clearly justify the locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.