Back to skill

Security audit

Google Weather

Security checks for vulnerabilities and agentic risk

Overview

This weather skill uses a Google API key to send requested locations to Google for weather and geocoding, which matches its stated purpose and is disclosed in the skill documentation.

Install only if you are comfortable providing a Google API key and having the locations you ask about sent to Google for geocoding and weather lookup. Review API key restrictions and billing controls in Google Cloud before use.

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)

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

The module performs network calls to Google APIs via requests.get, yet the static finding says network capability is not covered by declared permissions. Undeclared network access creates a trust and containment problem: the same mechanism used for weather lookups could also transmit sensitive user input or secrets externally without platform enforcement.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

The module performs network calls to Google APIs via requests.get, yet the static finding says network capability is not covered by declared permissions. Undeclared network access creates a trust and containment problem: the same mechanism used for weather lookups could also transmit sensitive user input or secrets externally without platform enforcement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file embeds Hebrew-specific condition translations and hardcodes quick-lookup locations exclusively for Israeli cities, which indicates a locale-specific default behavior. Because this regional/language bias is not clearly documented as an opt-in or region-specific tool, it may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

User-supplied location data is sent to Google Geocoding and Weather APIs, but the code provides no disclosure or consent flow before transmitting that data externally. Location information can be sensitive, and silent third-party sharing may violate user expectations, privacy requirements, or enterprise data-handling rules.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill reads API credentials from environment variables and uses them in network requests to Google services. Although this is expected for API integration, the file lacks a user-facing warning or explanatory note that the skill depends on external credentials and will use them for outbound API calls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.