ClawHub
Back to skill

Security audit

portfolio-manager

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed portfolio-analysis skill that uses a Finskills API key for market data, with a privacy note because portfolio details are sensitive.

Install only if you are comfortable using Finskills for market-data lookups and sharing portfolio details with the agent workflow. Keep FINSKILLS_API_KEY in an environment variable or secret store, avoid providing unnecessary cost basis or personally identifying financial details, and verify recommendations before making investment decisions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
92% confidence
Finding
The README describes portfolio analysis features but does not clearly warn users that their holdings and cost-basis data may be sent to an external API provider. Portfolio composition and cost basis are sensitive financial information, and undisclosed transmission can create privacy, confidentiality, and compliance risk if users share data they would not otherwise expose.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill asks the user for sensitive financial data such as holdings, portfolio value, and cost basis, and then directs the agent to use an external API without clearly warning the user what information may be transmitted or retained. Even if the current documented endpoints only use tickers, the workflow tightly couples private portfolio context with third-party processing, creating a meaningful privacy and data-handling risk through over-sharing, logging, or future implementation drift.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal