Natural-Language Policy Violations
Medium
- Confidence
- 88% confidence
- Finding
- 整个技能说明、触发词和输出示例均默认且仅支持中文表达，没有提供用户语言选择或声明该技能仅面向中文用户。按组织语言/locale 政策，这种未说明的单一语言约束可能构成自然语言策略违规。
Security audit
MBTI Agent 人格测评
Security checks for vulnerabilities and agentic risk
Overview
This is an offline Chinese-language MBTI questionnaire and scorer with only minor transparency concerns around local result storage and broad triggers.
Install only if you want a Chinese-language MBTI-style assessment skill. Treat responses and generated type reports as local profile data, and check where your agent writes results before using it for personal or sensitive answers.
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
- 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
Findings (8)
Vague Triggers
Medium
- Confidence
- 93% confidence
- Finding
- The trigger phrases include broad, everyday requests such as asking for a personality test or MBTI evaluation, which can cause the skill to activate in contexts where the user did not explicitly intend to invoke this specific local skill. In an agent environment, unintended activation can lead to unexpected execution paths, privacy surprises, or local file writes via the associated test/results workflow.
Natural-Language Policy Violations
Medium
- Confidence
- 88% confidence
- Finding
- This code file contains natural-language docstrings and user-facing report text exclusively in Chinese, including the top-level description and later output labels. Under the policy, forcing a specific language without opt-in or a stated region-specific reason is a locale/language policy violation.
Missing User Warnings
Low
- Confidence
- 82% confidence
- Finding
- The documentation notes a results directory and implies persistent output, but it does not clearly warn users that assessment results may be written to local storage. This creates a transparency and privacy issue because users may disclose sensitive psychological or profiling-related information without realizing it will be retained.
Natural-Language Policy Violations
Low
- Confidence
- 91% confidence
- Finding
- This JSON file defines all user-facing questionnaire text and type descriptions in Chinese only, with no indication that users can opt into another language or locale. Under the policy criteria, forcing a specific language without user choice is a natural-language locale violation unless the constraint is explicitly documented and justified.
Natural-Language Policy Violations
Low
- Confidence
- 80% confidence
- Finding
- This file presents all instructions and questions in a single language without any opt-in or language-selection mechanism. Under the policy, forcing a specific language without user choice can be a natural-language policy violation unless the locale constraint is clearly documented and justified.
Missing User Warnings
Low
- Confidence
- 87% confidence
- Finding
- The skill tells users their answers will be submitted to a scoring system, but it provides no information about what data is collected, where it is sent, how it is stored, or whether the responses may be linked to a person. Even though MBTI-style answers are not highly sensitive by default, undisclosed transmission and profiling can create privacy and trust risks.
Natural-Language Policy Violations
Low
- Confidence
- 91% confidence
- Finding
- This JSON result embeds user-facing descriptive fields entirely in Chinese ("调停者", "价值守护者，真诚创造，追求真实与意义") with no indication that language selection is optional or locale-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern applicable to all file types.