Back to skill

Security audit

questionnaire-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple questionnaire generator with no code execution, persistence, or sensitive data access.

This skill appears safe to install for generating usability questionnaires. Users should be aware that the packaged documentation is mostly in Chinese, but the runtime instruction says responses should follow the user's language.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README is entirely written in Chinese and presents the skill workflow, examples, and outputs only in Chinese, without indicating that users may choose another language. This can constitute a language/locale policy violation because it implicitly constrains interaction language without explicit opt-in or a documented justification.

Content

No source excerpt is available for this finding.