Security audit

Agent Mbti

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language MBTI-style questionnaire skill for describing an agent's behavior and user preferences, with no code execution, network access, or persistence found.

Use this skill if you want an informal Chinese-language MBTI-style assessment of an agent's behavior and your preferred interaction style. Review any recommendations before applying them as agent configuration, and do not treat the output as a clinical or scientifically rigorous personality evaluation.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill description uses very broad triggers like testing agent personality, adjusting behavior, or customizing communication style, which can match many ordinary conversations about agents. This can cause the skill to activate unexpectedly and steer unrelated interactions into its workflow, creating prompt-routing confusion and increasing the chance of unintended data collection or behavior shaping.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: Most instructional content and output examples are presented only in Chinese, which can force a specific language experience on users or operators without opt-in. The file does not indicate that the skill is region-specific or that users may choose another language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This JSON skill defines the name, description, title, and user-facing guidelines entirely in Chinese, with no indication that other languages are supported or that Chinese is an optional locale. Because SQP-3 applies to all file types, this is a natural-language locale policy issue when no user opt-in or documented regional justification is present.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The T/F questions and answer labels are internally inconsistent with the scoring key. For example, some prompts present option A as empathy/feelings and B as logic, while other prompts invert whether A/B correspond to thinking versus feeling in a way that can misclassify respondents. In a personality-diagnosis skill, this undermines integrity of the assessment and can produce systematically wrong personality outputs and downstream configuration recommendations.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The J/P dimension also contains contradictions between question wording and the scoring key, causing answers that indicate planning/organization to sometimes be scored as the opposite trait. Because this file drives automated personality typing, the inconsistency can distort results, reduce trust, and lead to incorrect agent-behavior tuning recommendations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This file's natural-language content is exclusively Chinese and does not indicate that the skill is region-specific or that users can opt into that language, which may force a specific language experience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: SQP-3 applies to all file types and flags language-policy violations when a skill forces a specific language without user opt-in. This markdown file presents all instructions and scoring guidance only in Chinese, with no indication that the skill is China-specific or that users may choose another language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The user-facing name, description, questions, scoring text, and output descriptions are all written in Chinese, with no indication that users can choose another language or that the survey is intentionally limited to a Chinese-language audience. This creates a natural-language locale constraint that is not documented as optional or region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.