Back to skill

Security audit

Fund Report

Security checks across malware telemetry and agentic risk

Overview

This is a simple fund-reporting skill with no executable code in the package; it looks benign, but the referenced Python script is not included for review.

This skill appears benign as submitted, but it is documentation-only. Before running any fund_report.py obtained from the linked repository or elsewhere, inspect that script and its dependencies, especially because financial quote tools commonly make network requests and may handle locally configured fund lists.

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

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.