ClawHub
Back to skill

Security audit

Weather Forecast

Security checks for vulnerabilities and agentic risk

Overview

This weather skill is purpose-aligned: it fetches user-requested forecast data from Open-Meteo and does not show hidden persistence, credential use, destructive behavior, or unrelated data access.

Before installing, understand that weather queries will send the requested coordinates and selected weather fields to Open-Meteo. Avoid using precise personal coordinates if you do not want that location shared with the weather API.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs execution of a network-capable script (`scripts/get_weather.py`) but the manifest does not declare any explicit tool scope such as `permissions` or `allowed-tools`. This creates an authorization ambiguity where runtime policy may be overly permissive or inconsistent, increasing the risk of unintended outbound requests or future abuse if the script behavior changes.

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The module docstring states the script fetches hourly temperature forecasts for a given location, implying a temperature-focused capability. In contrast, the implementation accepts any comma-separated hourly parameter string and sends it to Open-Meteo, enabling retrieval of non-temperature data too.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest says the skill provides access to Open-Meteo for getting hourly temperature forecasts, but the code exposes a generic `hourly_params` input and forwards it directly to the API. This expands the behavior from temperature-only retrieval to arbitrary hourly weather data, which is broader than the stated scope.

External Transmission

Medium
Category
Data Exfiltration
Content
raise ValueError(f"Invalid longitude: {longitude}. Must be between -180 and 180")

    # Build API URL
    base_url = "https://api.open-meteo.com/v1/forecast"
    params = {
        "latitude": str(latitude),
        "longitude": str(longitude),
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
raise ValueError(f"Invalid longitude: {longitude}. Must be between -180 and 180")

    # Build API URL
    base_url = "https://api.open-meteo.com/v1/forecast"
    params = {
        "latitude": str(latitude),
        "longitude": str(longitude),
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
raise ValueError(f"Invalid longitude: {longitude}. Must be between -180 and 180")

    # Build API URL
    base_url = "https://api.open-meteo.com/v1/forecast"
    params = {
        "latitude": str(latitude),
        "longitude": str(longitude),
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
raise ValueError(f"Invalid longitude: {longitude}. Must be between -180 and 180")

    # Build API URL
    base_url = "https://api.open-meteo.com/v1/forecast"
    params = {
        "latitude": str(latitude),
        "longitude": str(longitude),
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
raise ValueError(f"Invalid longitude: {longitude}. Must be between -180 and 180")

    # Build API URL
    base_url = "https://api.open-meteo.com/v1/forecast"
    params = {
        "latitude": str(latitude),
        "longitude": str(longitude),
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.