Gas Price Alert

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:43 AM UTC
• Version:
  1.1.0

Overview

This skill is a disclosed gas-station lookup and optional alert helper, but users should treat prices and non-Columbus results as approximate.

Install only if you are comfortable sending searched ZIP codes or coordinates to external mapping or gas-price services. Treat displayed prices as estimates unless using a real price source, be cautious with non-Columbus searches, and review any cron alert so it does not keep sending location-based requests after you no longer need it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill documentation instructs users to run scripts that perform network access and write output files, but the skill declares no permissions. This creates a transparency and governance problem: operators and users cannot accurately assess what capabilities the skill uses, and an agent framework may execute it with broader effects than expected.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The documented behavior materially overstates what the skill does and omits important implementation details such as browser-based scraping, local file output, hardcoded location assumptions, and the lack of actual alerting/monitoring logic. This mismatch can cause users or orchestrators to trust the skill with workflows it cannot safely or accurately perform, and hidden scraping or persistence behavior increases operational and compliance risk.

Description-Behavior Mismatch

Medium

• Confidence: 96% confidence
• Finding: The skill description promises gas price finding for any US location, but the implementation is anchored to Columbus-specific defaults and hardcoded Costco locations, while most returned stations have no real price data. This creates a deceptive-output integrity issue: users may rely on incomplete or estimated results as if they were nationwide and current, which can mislead downstream actions or automations.

Intent-Code Divergence

Low

• Confidence: 87% confidence
• Finding: The code computes station distance using a default downtown Columbus reference rather than the user-supplied search location, despite presenting the search as location-based. This can cause incorrect filtering and ranking of stations, producing inaccurate results that undermine trust and may misdirect users.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill describes scheduled Telegram notifications containing location-derived gas price results without warning users about privacy implications. Repeated delivery of destination-specific or home-area searches can expose sensitive location patterns, especially when sent through third-party messaging services or retained in chat history.

VirusTotal

64/64 vendors flagged this skill as clean.