ClawHub
Back to skill

Security audit

Wikipedia Nearby

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Wikipedia nearby-search helper, with the main privacy consideration that coordinates used for searches may be sent to Wikipedia APIs.

Before installing, be aware that searches based on your exact coordinates, including locations shared from Telegram or WhatsApp, can be sent to Wikipedia APIs to retrieve nearby articles. Use a place name or approximate area when you do not want to share precise coordinates.

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
  • 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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says to use the skill when the user asks about "nearby places" or "what's around me," which are broad phrases that can arise in many contexts unrelated to Wikipedia geosearch. The trigger guidance does not provide exclusions or constraints to limit invocation to explicit Wikipedia-nearby lookups.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to extract precise latitude/longitude from Telegram or WhatsApp location messages and send them to Wikipedia APIs without an explicit user-facing notice or consent step. That creates a privacy leak because exact location data can reveal home, work, or travel patterns, and the risk is heightened by the workflow's emphasis on directly forwarding shared coordinates to a third-party service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.