Security audit

Information Services

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent location, weather, and time helper, but it can infer precise location and contact external services without clear user control.

Review before installing. Use this only if you are comfortable with an agent accessing precise or approximate location sources and contacting external weather/time services. Prefer manual city or coarse-location input, require confirmation before GPS/system/IP/WiFi/cellular lookup, and only provide optional geolocation API keys when needed with provider-side restrictions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (11)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger list uses extremely broad, common terms such as "location," "weather," and "time," which can cause the skill to activate in many benign conversations unrelated to an explicit user request for this capability. In a location-aware skill, unintended invocation is more dangerous because it may initiate privacy-sensitive flows or expose contextual data more often than users expect.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill advertises GPS, IP, WiFi, and cellular geolocation plus external weather/time services and credential use, but provides no user-facing disclosure about collection, transmission, retention, or consent for sensitive location data. In this context, the omission is meaningful because the skill is explicitly designed to process potentially precise geolocation, which raises privacy and data-handling risk even if the underlying implementation is otherwise legitimate.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The prompt explicitly instructs the skill to use privacy-sensitive location sources such as GPS, WiFi, cellular, and IP, and to execute all services when intent is ambiguous or multiple intents are detected. That combination can cause unnecessary collection or disclosure of precise location and related contextual data without clear user consent, minimization, or a warning about privacy handling.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documentation advertises collection and use of sensitive location-related signals such as GPS, IP, WiFi, and cellular data, plus network-based weather and time queries, without disclosing privacy implications, data transmission, retention, or third-party sharing. In a location-aware skill, this omission can mislead users into exposing precise whereabouts and device/network metadata without informed consent.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The workflow explicitly attempts GPS, system, and IP geolocation in sequence, which can collect and infer sensitive location data without any user-facing notice, consent, or scope limitation. In an agent skill context, silent location lookup is privacy-sensitive because it may expose precise whereabouts and hardware/network-derived signals to the skill and downstream services without the user realizing it.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: Sending coordinates or location-derived data to external weather providers creates a network disclosure of potentially sensitive location information. Because the workflow does not warn the user that their location will be transmitted to third-party services such as wttr.in or open-meteo, it introduces a meaningful privacy and data-sharing risk.

Missing User Warnings

Low

Confidence: 82% confidence
Finding: Querying pool.ntp.org involves external network access, and the workflow does not disclose that an outbound request may occur. While NTP requests are generally low sensitivity compared with geolocation, undisclosed network activity can still matter in restricted, privacy-conscious, or air-gapped environments.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The file documents location collection across GPS, IP, WiFi, cellular, and third-party API-assisted geolocation without any warning about privacy implications, consent requirements, or possible transmission of sensitive location data to external providers. In a location-aware skill, this omission can lead users or downstream implementers to collect precise geolocation or send network-derived identifiers to outside services without informed consent, creating privacy, compliance, and data-handling risk.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger set includes very generic words such as "weather," "time," and "when," which can match ordinary conversation and cause unintended skill activation. In a location-aware skill, accidental invocation can lead to unnecessary use of sensitive data sources or external lookups, increasing privacy and operational risk even without explicit malicious behavior.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The document describes fallback chains that include IP, WiFi, cellular, external weather APIs, NTP, and web APIs, but it does not require a user-facing warning or consent notice before those sources are used. This is dangerous because users may unknowingly expose location-derived metadata or trigger third-party data sharing, especially when the system infers location from non-obvious sources like IP address.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The specification explicitly instructs the skill to determine the user's location through several sources and then send coordinates to external weather providers, but it does not mention any user notice, consent flow, or data-minimization controls. This creates a real privacy risk because precise location data can be sensitive, and transmitting it to third-party services without clear disclosure can expose users to unwanted tracking or regulatory/privacy compliance issues.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal