Back to skill

Security audit

教案设计助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple lesson-plan writing helper with no evidence of hidden code, data collection, persistence, or privileged actions.

This appears safe to install for lesson-plan drafting. Users should be aware it may activate on broad teaching-related phrases, and teachers should still review outputs for curriculum fit, student privacy, safety, and professional accuracy.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are very broad, generic education terms such as '写教案', '备课', and '教学目标' that can appear in many normal conversations. This can cause the skill to activate when the user did not specifically intend to use it, creating prompt-scope confusion and increasing the chance of irrelevant or policy-bypassing behavior through unintended routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language examples are open-ended and broadly phrased, for example '帮我把一节课的教学目标、重难点、活动与作业一次写全' and '把这些整理成一张表', without constraints that clearly limit when this skill should be selected. Such ambiguity can cause overmatching, where the skill is invoked for general editing or education requests outside its intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.