ClawHub
Back to skill

Security audit

Loops

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed Loops connector helper, with state-changing actions identified and confirmation required before writes or deletion.

Install this only if you intend to let the agent operate your Loops account through OOMOL. Review write and delete payloads carefully before approving them, especially contact deletion, contact updates, and event sends that may trigger automations.

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
95% confidence
Finding
The trigger text is overly expansive: 'Use this skill for ANY Loops request' and 'Whenever a task involves Loops' can cause the agent to invoke this skill for loosely related tasks without sufficient scoping. In an agentic environment, broad routing increases the chance of unnecessary access to connected third-party data or accidental execution of write/destructive actions when a user merely mentions Loops.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.