Back to skill

Security audit

刷题网页生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill generates offline quiz HTML apps and its persistence and file output are aligned with that purpose.

Safe to install for generating offline quiz pages. Before sharing generated apps with students, add or verify a clear notice that scores and wrong-answer history are saved in the browser, include a way to clear local records, and use care when importing JSON records from untrusted sources.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs automatic invocation whenever the user mentions broad, common phrases related to quizzes or tests, even if they did not explicitly request this skill. That increases the chance of unauthorized tool activation, context hijacking, or bypass of normal user-intent confirmation, especially in systems where skills may have side effects such as file generation or overwriting outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill mandates localStorage persistence plus export/import of study records, but does not require any user-facing disclosure that learning history, wrong-answer records, and scores will be stored locally and may be exported as files. This can expose sensitive educational data on shared devices or lead users to import untrusted JSON without understanding the privacy and integrity implications.

Content

No source excerpt is available for this finding.