Back to skill

Security audit

投资者认知基石书单

Security checks across malware telemetry and agentic risk

Overview

This is a static investment reading-list skill, with no code execution or hidden access, but users should treat it as educational rather than personal financial advice.

Install this as an educational reading and concepts guide. Do not treat its summaries, valuation formulas, or reading paths as personalized financial, legal, or tax advice; verify important claims and consult a qualified professional before making investment decisions.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation examples use very broad phrases such as asking for a beginner investment book or how to handle uncertainty, which can cause the skill to trigger in overly general conversations. In a financial domain, ambiguous invocation increases the chance the agent offers investment-oriented guidance when the user did not explicitly request this specialized skill, creating scope creep and possible misleading guidance.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill provides investment guidance, frameworks, and usage pathways without stating that the content is educational and not personalized financial advice. In this context, users may reasonably treat the recommendations as actionable advice, which is risky because the skill does not assess suitability, risk tolerance, jurisdiction, or financial circumstances.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.