ClawHub
Back to skill

Security audit

天气

Security checks for vulnerabilities and agentic risk

Overview

This weather skill is a simple wttr.in query guide with no hidden code or persistence, though users should know location queries go to an external service.

Installers should understand that weather lookups will contact wttr.in and share the location string being queried. Avoid using exact home addresses or other sensitive locations unless that disclosure is acceptable.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs users or an agent to send user-supplied city/location queries to the third-party service wttr.in, but it does not clearly disclose that this transfers user input off-platform. Even though the data appears low sensitivity in normal weather use, locations can still reveal personal context such as home area, travel plans, or current whereabouts, so the missing disclosure is a real privacy weakness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.