Back to skill

Security audit

IELTS Grading Skill

Security checks for vulnerabilities and agentic risk

Overview

This IELTS grading skill is a plain Markdown guide for scoring user-provided writing or speaking responses, with disclosed web lookup for prompt verification and no executable or persistent behavior.

Before installing, understand that writing-task grading expects web searches to confirm the IELTS prompt. Do not include personal identifiers, candidate numbers, or private exam-session details unless needed; ask for a local-only or no-web review if you only want rubric-based feedback.

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
  • 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
92% confidence
Finding

The skill requires web searches using user-provided exam prompt details, but it does not instruct the agent to obtain consent, minimize shared data, or warn the user that their text may be sent to external services. This creates a privacy risk because user-supplied writing, remembered prompts, exam session details, or identifiers could be exposed to third-party search providers unnecessarily.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file specifies '默认中文' for output, which imposes a language choice by default rather than asking the user for their preferred language. This is a natural-language policy concern because it forces a locale/language behavior without explicit opt-in or a documented justification.

Content

No source excerpt is available for this finding.