Back to skill

Security audit

Xueersi Word Story Memory

Security checks for vulnerabilities and agentic risk

Overview

This is a simple educational vocabulary-mnemonic skill with no code execution, network access, credential use, persistence, or hidden behavior.

Install this if you want Chinese-language mnemonic support for English vocabulary. It appears low risk, but it is not ideal for English-only learners unless they explicitly want Chinese definitions and translations.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata explicitly frames the tool as Chinese-mnemonic output for K-9 learners and does not indicate any language preference check. This can override user locale expectations or reduce accessibility for users who do not read Chinese, creating a quality/safety issue around inappropriate localization rather than a direct security exploit.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The required output format hard-codes Chinese definitions and translations, which removes user choice and may expose learners to content in a language they did not request. In an educational skill this is mainly a consent/accessibility and localization-control issue, not evidence of malicious behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.