ClawHub
Back to skill

Security audit

Hoop

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Hoop read-only connector skill, with disclosed setup and credential handling, and no evidence of hidden or destructive behavior.

Install only if you intend to use OOMOL's oo CLI with a connected Hoop account. Be aware it can read Hoop profile, connection, and session data through that connection, and review the CLI installer and account scopes before completing first-time setup.

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
90% confidence
Finding
The trigger phrase directs the agent to use this skill for "ANY Hoop request," which is broader than necessary and can cause the skill to be invoked in situations where a narrower or safer workflow would be more appropriate. Because the skill exposes a generic connector runner and includes setup/auth guidance, over-invocation increases the chance of unnecessary access to Hoop data or execution of unintended operations if the skill later expands beyond read-only actions.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.