ClawHub
Back to skill

Security audit

Weather

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward China weather lookup tool that sends user-requested locations to Open-Meteo and does not show hidden persistence, credential access, or unrelated behavior.

Install only if you are comfortable with city names, districts, or coordinates you ask about being sent to Open-Meteo over HTTPS. Do not use exact private coordinates unless needed, and check official local authorities for severe-weather warnings.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to run a bundled Python script that makes outbound HTTPS requests, but the manifest does not declare any tool scope such as allowed network access. This creates a policy and containment gap: an agent/runtime may permit broader network behavior than intended or fail to enforce least privilege, making later code changes or prompt abuse harder to constrain.

External Transmission

Medium
Category
Data Exfiltration
Content
from typing import Any

GEOCODING_URL = "https://geocoding-api.open-meteo.com/v1/search"
FORECAST_URL = "https://api.open-meteo.com/v1/forecast"
USER_AGENT = "china-weather-skill/1.0 (+https://clawhub.ai/)"
CHINA_CODES = {"CN", "HK", "MO", "TW"}
Confidence
87% confidence
Finding
The skill transmits user-supplied location data or precise latitude/longitude to third-party Open-Meteo endpoints over the network. While this is necessary for functionality and uses HTTPS, it is still an external data disclosure path that can reveal sensitive location information, especially when users provide exact coordinates or identifiable place names.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The geocoding request hard-codes `language: "zh"`, and the rest of the skill renders all user-facing output in Chinese. The policy for natural-language violations applies to all file types and flags language or locale constraints when the skill does not provide user choice or clearly document a justified region-specific exception.

Static analysis

No suspicious patterns detected.