Price Monitor

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:16 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed price-monitoring helper that visits user-specified pages and writes local price history, with no evidence of hidden exfiltration or destructive behavior.

Install only if you are comfortable with a skill that can open user-listed webpages through agent-browser and write local price-history files. Review the product CSV before running it, avoid private or restricted sites unless authorized, protect retained history logs, and manually review any cron schedule or future webhook/email configuration before enabling it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill documentation clearly instructs use of shell commands, browser automation, and local file writes, but the manifest does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: users or orchestrators may invoke a skill believing it is lower-privilege than it actually is, increasing the chance of unintended file access or command execution.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The description is broad enough to activate on many generic website-monitoring or web-content tasks, which can cause the skill to be selected in contexts beyond price tracking. Because the skill includes browser automation, shell usage, and data logging, overbroad activation increases the risk of unintended use on sensitive sites or workflows.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The skill advertises alert notifications, email, Discord webhooks, and similar integrations without clearly warning that monitored URLs, prices, stock status, or page-derived content may be transmitted to third-party services. This can lead to unintentional data disclosure, especially if users monitor non-public or business-sensitive pages.

Missing User Warnings

Low

• Confidence: 79% confidence
• Finding: The documentation instructs users to append monitored data to local history files without warning that this creates persistent storage. While logging is expected for a monitoring skill, retained records can expose browsing targets, pricing intelligence, or other collected content to later local access or mishandling.

VirusTotal

66/66 vendors flagged this skill as clean.