Security audit

HUMAN 3.0 Life Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language life assessment skill with sensitive personal-development questioning, but it contains no code execution, persistence, credential access, or hidden data flow.

Install this only if you want a Chinese HUMAN 3.0 personal-development assessment. Expect direct feedback and questions about health, relationships, work, finances, AI use, obsessive focus, extreme life changes, and related sensitive topics; treat the output as coaching-style guidance, not medical or mental-health advice.

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

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 (8)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The activation phrases include broad, everyday requests such as '人生指导', '人生规划', and '我的人生出了什么问题', which can cause the skill to trigger in situations where the user did not explicitly request this specific HUMAN 3.0 framework. In a skill that performs quasi-diagnostic personal assessment and steers a multi-step interview, unintended activation can lead to confusing, overreaching, or manipulative interactions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 99% confidence
Finding: Mandating Chinese-only interaction without checking the user's language preference can exclude users, cause misunderstanding, and undermine informed participation in a sensitive life-assessment flow. In this context, poor comprehension is especially risky because the skill makes evaluative judgments and gives developmental advice that users may misinterpret.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Requiring the opening script to be delivered only in Chinese removes user choice at the first point of interaction, increasing the chance that users will not understand the nature of the assessment or what they are consenting to. Because the script introduces a direct, potentially sensitive evaluative process, lack of comprehension weakens transparency and safe use.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Forcing the final report to be in Chinese regardless of user preference can make the output inaccessible or misleading, especially when it contains nuanced judgments about personal development and recommended next steps. In a skill that produces structured advice, language mismatch reduces usability and can cause harmful misunderstanding of recommendations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: This markdown file is largely written in English, but the probing questions section switches to Chinese for all quoted prompts. That imposes a specific language on users without opt-in or explanation, which matches the language/locale policy violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The interview bank is written entirely as Chinese-language questioning and does not provide a language-choice step or fallback behavior. While not a classic security flaw, this can cause consent and safety misunderstandings in a sensitive assessment workflow, making it easier for users to misinterpret probing questions or disclose information without fully understanding the framing.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file instructs the agent to proactively ask about obsession, regression, heavy AI use, and extreme life changes without any consent check, sensitivity warning, or escalation boundaries. In a life-planning and developmental assessment context, these prompts can elicit highly sensitive mental-health-adjacent information and may intensify distress or normalize unsafe disclosure patterns, especially for vulnerable users.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The line explicitly states this is a Chinese-language assessment report template, which imposes a specific language requirement. Under the policy, forcing a language without user opt-in is a natural-language policy violation unless the locale constraint is clearly justified, which is not present here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.