Security audit

Free Weather Skill Tool Free

Security checks across malware telemetry and agentic risk

Overview

This weather skill is mostly purpose-aligned, but it asks for broad write and command authority and uses overly broad activation language for a simple weather-query tool.

Review before installing. The weather API behavior is understandable, but the skill should ideally narrow its trigger conditions to weather-only requests and limit write use to explicit exports in safe paths. Avoid using sensitive home, travel, or client locations unless you are comfortable sending that query to wttr.in or Open-Meteo.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Context-Inappropriate Capability

Medium

Confidence: 92% confidence
Finding: File write access is unnecessary for a query/display-oriented weather skill except for narrowly scoped optional export features. Allowing arbitrary writes can be abused to drop files, alter user data, or persist artifacts on the host if the skill is invoked in broader agent workflows.

Context-Inappropriate Capability

Medium

Confidence: 92% confidence
Finding: File write access is unnecessary for a query/display-oriented weather skill except for narrowly scoped optional export features. Allowing arbitrary writes can be abused to drop files, alter user data, or persist artifacts on the host if the skill is invoked in broader agent workflows.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger conditions are overly broad, covering generic coding, debugging, and deployment-related requests rather than only weather queries. This increases the chance the skill is selected in unrelated contexts where its exec/write permissions and network behaviors create unnecessary exposure.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The capability coverage section uses broad, generic keywords without meaningful boundaries, which can cause accidental routing of unrelated requests to this skill. In an agent ecosystem, overbroad matching amplifies the risk of unnecessary external requests and misuse of privileged tools.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill sends user-supplied city/location data to third-party services but does not clearly warn users about external transmission or privacy implications. Even seemingly low-sensitivity queries can reveal travel plans, rough location interests, language preferences, or usage patterns to external providers.

Missing User Warnings

Low

Confidence: 80% confidence
Finding: The examples write PNG files to /tmp but the skill does not clearly disclose file-write side effects. Undocumented writes can surprise users, expose filenames containing user input, and create risks when combined with broader write permissions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.