Back to skill

Security audit

Weather

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this weather skill as benign, with the main caveat that its weather lookup may send your location to an external service without a privacy warning.

Before installing, consider whether you are comfortable sharing the location you request with wttr.in. Prefer city-level locations if that is enough for your forecast.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Weather lookup instructions omit a privacy warning about sending the user's requested location to a third-party service.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow instructs the agent to request weather from wttr.in using a location, which line 26 allows to be precise coordinates. Although the service URL is shown, the skill does not warn users that their location will be transmitted to an external provider; the external-content warning addresses response safety rather than location privacy.

Content

No source excerpt is available for this finding.