Back to skill

Security audit

SBTI 人格测评

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese SBTI personality-test helper with some documentation inconsistencies, but no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install only if you are comfortable with a Chinese-language entertainment questionnaire that uses crude humor and has inconsistent documentation around the hidden DRUNK result. It appears locally contained and low-risk, but its advertised question/type count should be fixed for accuracy.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The code generally aligns with the declared purpose of an SBTI personality test calculator: it computes dimension scores, maps them to personality patterns, and returns a personality result. However, there are material content mismatches in the core test definition. The description says the assessment has 31 questions, but the code explicitly requires exactly 30 answers and maps only Q1–Q30. It also claims 27 personality types, but the actual scoring dictionary contains 26 selectable type patterns; although TYPE_NAMES/TYPE_INTROS include an extra 'DRUNK' entry, that type is never used in matching because it is absent from TYPES. These discrepancies affect the substantive behavior of the skill rather than being minor implementation details.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file uses a single fixed language throughout the skill description, trigger phrases, workflow, and user-facing output examples. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which it is not here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all user-facing questionnaire content exclusively in Chinese and does not provide any opt-in, alternative language, or statement that the skill is intended only for Chinese-speaking users. Under the policy rule for language or locale constraints, this is a natural-language policy issue because the file effectively enforces a specific language by default.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest says the skill is for a 31-question SBTI assessment, but this file documents and enforces a 30-answer input format. The module docstring states '输入30题答案' and the code rejects any input not of length 30, so the implemented behavior does not match the described test scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The entire skill content is written only in Chinese and does not indicate any option for alternate language or locale. Under the stated policy, a language constraint can be a natural-language policy issue when the skill does not offer user opt-in or clearly document a justified locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code's docstring, CLI usage text, and formatted results are all hard-coded in Chinese, which creates a locale-specific user experience without any opt-in or alternative language support. The policy explicitly calls for flagging language or locale constraints when the skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The comment explicitly documents the mapping as 'Q1-Q30', which conflicts with the skill's stated purpose of running a 31-question SBTI test. This is more than an omission because the code comments affirm a different test definition than the manifest advertises.

Content

No source excerpt is available for this finding.