Back to skill

Security audit

错题解析与讲评稿

Security checks for vulnerabilities and agentic risk

Overview

This is a simple educational prompt skill for analyzing wrong answers and producing teaching notes, with no code or hidden data access.

Safe to install for classroom or tutoring use. Be aware that broad Chinese educational phrases may invoke it when you are discussing similar tasks, and avoid including unnecessary student personal information in prompts.

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
89% confidence
Finding

The trigger list contains short, generic phrases such as “错题分析” and “讲评稿” that are likely to appear in ordinary educational conversations. Overly broad activation phrases can cause the skill to trigger unintentionally, leading to context hijacking or unexpected handling of user content by this skill instead of the user’s intended workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language example includes broad everyday wording like “帮我把一道题讲透,” which is a normal instructional request and may be said without any intent to invoke a specific skill. This increases the risk of accidental activation, especially in educational chat contexts where such phrasing is common, causing ambiguous routing and unintended execution of the skill behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.