Back to skill

Security audit

自学教练

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps teachers generate local study-guide and quiz HTML files, with disclosed local browser storage and no evidence of hidden execution, exfiltration, or privilege-seeking behavior.

Install only if you want a Chinese-language teaching helper that generates single-file HTML study and quiz pages. Share generated HTML and imported progress JSON only between trusted teachers and students, because local HTML can run JavaScript and imported JSON can affect saved quiz progress.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to match many ordinary education-related requests, which can cause the skill to activate when the user did not specifically ask for this tool. Over-broad routing increases the chance of unintended behavior, content hijacking, or suppression of better-matched skills, especially because the skill generates executable HTML/JS artifacts from user-provided materials.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill promotes distributing AI-generated local HTML files that use browser localStorage and JSON import/export, but it does not warn teachers or students about the trust boundary this creates. Opening untrusted HTML locally can still execute JavaScript, manipulate locally stored study data, and import malformed or hostile JSON that causes data loss, spoofed content, or privacy leakage if users share exported progress files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill's display name and core description are entirely in Chinese, and the document does not indicate that users may choose another language or locale. This can constitute a language policy issue when the skill implicitly assumes one language for all users without documenting opt-in or regional limitation.

Content

No source excerpt is available for this finding.