Back to skill

Security audit

NBTI

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language meme personality quiz with no code or system access, but its mental-health language should be treated as entertainment only.

Install this only if you want a Chinese meme-style personality quiz. Do not treat its results as psychological or medical advice, and avoid using it when someone is expressing real distress, self-harm, depression, anxiety, or other serious mental-health concerns.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are broad enough to activate on generic discussions about mental state, personality, or shared test results, which can cause the skill to intervene in contexts where users may be discussing real emotional distress. In a mental-health-adjacent context, unintended activation increases the risk of trivializing serious conversations and delivering inappropriate quiz content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill presents itself as a mental-state or personality test and only later includes a joking disclaimer, without a clear upfront warning that it is entertainment-only and not suitable for assessing psychological wellbeing. Because it uses mental-health framing such as “精神状态” and “脑干缺失,” users may misunderstand the output as meaningful assessment, especially vulnerable users seeking reassurance or self-diagnosis.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all user-facing content exclusively in Chinese and does not indicate that language selection is optional or configurable. Under the natural-language policy rules, forcing a specific language without user opt-in is a locale/language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill content and output guidance are written in Chinese, and the instructions for result style assume Chinese-language output without any opt-in or alternative locale. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction “中文提问,中文结果” requires a single language for all interactions. This is a language/locale policy issue because the file does not provide user opt-in, fallback behavior, or justification for limiting the skill to Chinese only.

Content

No source excerpt is available for this finding.