Eric's Life Wisdom

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Chinese life-advice skill with opinionated coaching content, not a skill that runs code, accesses data, or changes the user's environment.

Install this only if you want a Chinese, strongly opinionated coaching style for life, career, wealth, education, and relationship reflection. Do not rely on it as professional financial, legal, medical, or mental-health advice, and be aware that its broad triggers may shape ordinary advice requests through one specific worldview.

SkillSpector

By NVIDIA

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 (7)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The activation description is very broad and covers many common topics like life choices, career development, wealth, education, and relationships, which can cause the skill to trigger for large numbers of ordinary user queries. Over-broad triggering is dangerous because it can unexpectedly override more appropriate skills or system behavior and steer users into a strongly opinionated framework without explicit consent.

Natural-Language Policy Violations

High

Confidence: 85% confidence
Finding: The skill content is entirely written to operate in Chinese and does not offer a user-choice mechanism for language, which can force responses into a locale the user did not request. This becomes more dangerous in a broad-activation skill because accidental triggering can degrade comprehension, exclude users, and increase the chance that important advice is misunderstood.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger scope is very broad, covering common topics like life choices, career development, wealth, and education, which can cause the skill to activate in many ordinary conversations without clear consent or precise routing boundaries. In this file, that risk is amplified because the skill then applies a strong ideological framing and prescriptive persona, increasing the chance of inappropriate or overconfident guidance in contexts that may need neutral, specialized, or safety-bounded advice.

Natural-Language Policy Violations

Medium

Confidence: 78% confidence
Finding: The skill metadata and content are written to operate in Chinese-centric style without any indication of respecting the user's language preference or obtaining opt-in. While not directly a code-execution risk, this can cause misrouting, reduced user comprehension, and accidental application of a specific linguistic and cultural framing to users who did not request it, which is more problematic here because the skill gives consequential life and wealth guidance.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The invocation guidance is extremely broad, mapping common life questions like career, money, education, emotions, and happiness to this skill. That can cause the agent to trigger in many loosely related conversations and steer users into a single ideological framework, increasing the chance of overreach, low-quality advice, or bypass of more appropriate domain-specific skills. In this context, the danger is amplified because the content makes sweeping claims about society, education, wealth, and human nature, which may be inappropriately applied as general-purpose guidance.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This content gives relationship advice through broad gender-based generalizations such as '大龄女性的婚恋策略' and claims about male/female incentives without user-specific context, caveats, or alternatives. In a life-advice skill, such framing can reinforce stereotypes, steer vulnerable users toward biased decisions, and produce unfair or emotionally harmful guidance when the model retrieves or mirrors this material.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The activation guidance maps very broad, everyday questions such as '我该怎么选', '我怎么改变命运', and '我该怎么看人' to this skill, which can cause it to trigger outside its stated niche and intercept general-purpose conversations. In a high-level life-advice skill with strong ideological framing, overbroad routing increases the chance of unsolicited persuasion, misapplication of advice, and bypass of more appropriate specialized skills.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal