Back to skill

Security audit

Weather

Security checks for vulnerabilities and agentic risk

Overview

This weather skill is a simple, disclosed set of weather-query instructions and does not show hidden execution, credential access, persistence, or unrelated data handling.

Installers should expect this skill to make outbound weather requests with the location they query. The artifact has some encoding/metadata quality issues, but no security-significant hidden behavior was found.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: weather-moji
description: "Get current weather and forecasts using Moji Weather for China-focused detailed forecasts"
tags: [domain-specific, general, api-integration, cli]

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description and main instructions explicitly position the skill as China-focused and present the usage/documentation in Chinese without indicating that users can choose another language or locale. This is a natural-language locale policy concern because the file imposes a specific language/region context rather than offering an opt-in or clearly documenting a justified region-only restriction.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

Free, no key, good for programmatic use:

bash
curl -s "https://api.open-meteo.com/v1/forecast?latitude=51.5&longitude=-0.12&current_weather=true"

Find coordinates for a city, then query. Returns JSON with temp, windspeed, weathercode.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The Chinese heading at L45 states the following wttr.in documentation is 'deprecated' or 'abandoned', but the subsequent sections provide full operational curl examples, tips, and formats for wttr.in and Open-Meteo. This is an intent/documentation contradiction because the text frames the capability as no longer used while still instructing users to use it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.