ClawHub
Back to skill

Security audit

Wikipedia Nearby

Security checks across malware telemetry and agentic risk

Overview

This skill is a lightweight Wikipedia nearby-search guide; it uses location data for its stated purpose but users should be mindful of precise-location privacy.

Install only if you are comfortable with your agent using a location you provide, or location data you intentionally share from browser or messaging apps, to query Wikipedia. For sensitive places, use an approximate place name or ask the agent to confirm before sending exact coordinates.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger guidance is broad enough to match common location-oriented requests like 'what's around me' or 'places near [location]', which can cause the skill to activate when the user did not specifically intend to use Wikipedia as the source. This is primarily a scope and routing issue rather than code execution, but it can lead to inappropriate handling of user queries and unnecessary collection or use of location context.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs handling precise latitude/longitude from Telegram or WhatsApp and sending them to Wikipedia's geosearch API, but it does not require an explicit privacy notice or consent step before using or transmitting that location data. Because location data is highly sensitive, this omission can expose users to privacy risks, especially if they did not expect their shared coordinates to be forwarded to a third party.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.