ClawHub

Weather Alert

Security checks across malware telemetry and agentic risk

Overview

This weather skill is coherent and purpose-aligned: it fetches forecasts from public weather APIs, prints alerts, and stores a local cache, with no evidence of hidden execution or malicious behavior.

Install only if you are comfortable sharing queried or monitored locations with public weather services. Review any host-level exec-event or scheduling integration before enabling automatic alerts, since that behavior would depend on the environment outside this script.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill config explicitly indicates automatic scheduled checks (`schedule_check: "6h"`) and a notification method of `exec-event`, but the user-facing description does not clearly warn that enabling alerts may trigger an external event mechanism without an immediate per-alert confirmation. This can lead users to authorize a weather skill expecting passive notifications while actually allowing periodic automated execution, which increases the risk of unintended command/event dispatch depending on how `exec-event` is implemented by the host environment.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script sends user-provided location names and coordinates to third-party weather services, which is a real privacy issue because precise geolocation can be sensitive personal data. In this skill context, external transmission is expected for functionality, but the lack of explicit user disclosure or consent makes the data sharing risk legitimate rather than purely incidental.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal