Back to skill

Security audit

weather

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a weather skill with one privacy disclosure gap, but no findings indicating harmful behavior, so the verdict is benign with high confidence.

Before installing, consider that weather lookups may send the location you provide to an external weather service. Use a city-level location if that is sufficient, and avoid sharing precise coordinates unless you are comfortable transmitting them.

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 user-provided locations to a third-party service.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The skill requests a city, region, airport code, or coordinates and instructs the agent to query wttr.in for weather. It does not warn that the supplied location will be transmitted to an external provider, which is particularly relevant when users supply precise coordinates.

Content

No source excerpt is available for this finding.