Back to skill

Security audit

Weather Stable

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward weather lookup skill that calls Open-Meteo and does not show hidden persistence, credential access, or unrelated behavior.

Reasonable to install if you are comfortable with city lookups being sent to Open-Meteo for non-preset cities. Operators in privacy-sensitive or non-China-locale environments should document or restrict the allowed Open-Meteo domains and consider adding configurable language/timezone settings.

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
  • 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 (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises network-capable behavior via its weather functionality and homepage/source references, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates a least-privilege and transparency gap: agents or reviewers cannot easily tell what external access the skill expects, making unintended or overbroad network use harder to control.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The geocoding request forces language=zh, and the script consistently emits Chinese text and uses a China-specific timezone, which constitutes a locale/language restriction. There is no user opt-in or configurable language selection, and the file does not indicate that this is an intentionally region-specific tool.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · weather-stable.sh (reported line 94)May include surrounding context.

sh
def fetch_weather(lat: float, lon: float) -> dict:
    url = (
        'https://api.open-meteo.com/v1/forecast'
        f'?latitude={lat}&longitude={lon}'
        '&current=temperature_2m,weather_code,wind_speed_10m'
        '&daily=temperature_2m_max,temperature_2m_min'

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README states that the skill requires outbound access to the Open-Meteo API, but it does not clearly disclose that user-supplied city queries will be transmitted to a third-party service. This is a real but low-severity privacy/transparency issue because users and operators may unknowingly send potentially sensitive location-related inputs off-box, especially in automated agent workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The phrase "Chinese and English city input" describes a language constraint in natural language. Because the file does not indicate that language support is user-selectable or justified as region-specific, it may conflict with the policy against forcing a specific language or locale without opt-in.

Content

No source excerpt is available for this finding.