Security audit

Zhang Yidong Macro Analysis

Security checks across malware telemetry and agentic risk

Overview

This is a finance-analysis prompt skill with no executable behavior, but users should treat its investment guidance as educational rather than personalized financial advice.

Use this skill for market-framework discussion and scenario analysis only. Do not rely on it as personalized investment advice, and verify current market data, sources, jurisdictional rules, risk tolerance, and suitability before making any financial decision.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly positions itself for investment decisions, asset allocation, and market timing without a clear disclaimer that outputs are general information rather than personalized financial advice. This can mislead users into acting on high-stakes recommendations unsuited to their risk tolerance, jurisdiction, or financial situation, creating tangible financial harm.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The example prompts and workflow directly invite buy/sell timing, position sizing, and allocation guidance without an accompanying financial-risk warning. Because the skill is framed as an expert analyst, users may over-trust these outputs and treat them as actionable recommendations, increasing the chance of losses from unsuitable or speculative decisions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.