Back to skill

Security audit

TOEFL Speaking Question Generator

Security checks for vulnerabilities and agentic risk

Overview

This TOEFL speaking practice skill is a simple Markdown-based study helper that generates questions and stores local practice history, with no executable code or network behavior found.

Install this if you want a Chinese-language TOEFL speaking practice workflow that keeps local records. Be aware that generating or changing a question set will update files under toefl/ and may retain generated answers and practice history.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and user interaction phrases are entirely in Chinese, and the skill does not indicate that language choice is optional or limited for a justified regional reason. This can violate language/locale policy when a skill effectively requires a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases include very broad everyday expressions such as “出题” and “换一个/换个话题”, which can be invoked accidentally in normal conversation and cause the skill to perform stateful actions. Because this skill reads and writes local files and changes persistent history, ambiguous activation increases the chance of unintended file modification and disclosure of stored answer content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly performs persistent writes to latest.md, history.json, and dated archive files, but the user-facing interaction description does not warn that invoking the skill modifies stored data. This creates a risk of silent state changes, accidental overwrites, and retention of potentially sensitive user-study artifacts without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The role and instructions are written in Chinese and implicitly require the skill to operate in Chinese, but the file does not offer any user opt-in or alternative language choice. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.