Security audit

One API key for real time stock equity pricing data including crypto BTC ETH etc.

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward market-data skill that uses a disclosed API key to fetch stock and crypto data from a disclosed provider.

Install this only if you are comfortable sending market-data queries to AIsa using your AISA_API_KEY. Tickers, dates, filters, and portfolio-style symbol lists may be logged by the provider or consume paid credits, so use a limited or dedicated API key where possible.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill metadata declares runtime requirements for environment variables and binaries, and the documentation clearly demonstrates network access using an API key, but it does not declare explicit permissions. This creates a transparency and consent problem: users may not realize the skill can access secrets and send authenticated requests to an external service.

Missing User Warnings

Low

Confidence: 95% confidence
Finding: The examples show authenticated requests to a third-party API using the user's bearer token, but they do not prominently warn that user-supplied tickers, filters, and other query parameters are transmitted off-platform and may consume paid credits. This can lead to unintended disclosure of sensitive research interests or accidental charges.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.