ClawHub
Back to skill

Security audit

HERE

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent HERE lookup helper that uses OOMOL's oo CLI for read-oriented location searches, with no artifact-backed signs of hidden or malicious behavior.

Install this if you want agents to perform HERE geocoding and place lookup through OOMOL. Review the oo CLI installer and OOMOL account connection first, and be aware that location queries you ask the agent to run will be sent through the OOMOL HERE connector.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description says to use this skill for "ANY HERE request" and "whenever a task involves HERE," which is an overly broad trigger that can cause the agent to invoke the skill for incidental mentions of HERE rather than clear HERE API tasks. This increases the chance of unintended external calls, unnecessary data exposure in queries, and bypassing more context-appropriate handling when the user did not actually request HERE-backed lookups.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.