Security audit

price-tracker

Security checks across malware telemetry and agentic risk

Overview

This price-tracking skill uses a real external API for current price lookups, but its historical-price feature fabricates random history while presenting it as decision-grade trend data.

Review before installing. Treat current-price comparisons as unverified leads, and do not rely on the price-history, trend, volatility, or prediction reports for resale or purchasing decisions unless the publisher replaces the mock history with real sourced data or labels it as simulation. Avoid submitting confidential sourcing, supplier, margin, inventory, or unreleased product lists unless you are comfortable sending them to SkillBoss.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Intent-Code Divergence

High

Confidence: 98% confidence
Finding: The function advertised as retrieving historical price data does not access any historical source and instead generates synthetic prices from the current price using random volatility. This is dangerous because users may make pricing, arbitrage, or purchasing decisions based on fabricated data presented as real market history, causing financial harm and undermining trust in downstream analysis.

Description-Behavior Mismatch

High

Confidence: 97% confidence
Finding: The skill metadata and script behavior imply genuine historical tracking and arbitrage analysis, but the implementation performs trend analysis and predictions over randomly generated synthetic data. In the context of a price-tracking skill intended to identify arbitrage opportunities, this mismatch is especially dangerous because it can directly mislead users into bad trades or false profit expectations.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill states that product queries and authenticated requests are sent to an external API, but it does not provide a clear user-facing privacy or data-sharing notice. Users may unknowingly send search terms, business research, or potentially sensitive product lists to a third party, creating confidentiality and compliance risks.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The script sends product names from the user-supplied CSV to an external search backend via search_product() without clearly disclosing that this data leaves the local environment. While product names are not always sensitive, CSV inputs can contain proprietary inventory lists, unreleased products, or other commercially sensitive data, so silent transmission to a third-party API creates a real data exposure risk.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The script sends user-supplied product keywords and extracted search-result content to an external API service without any explicit user notice or consent flow. In a skill context, this creates a privacy and data-governance issue because user inputs and derived data leave the local environment and are processed by a third party.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.