ClawHub
Back to skill

Security audit

Roam HQ

Security checks across malware telemetry and agentic risk

Overview

This Roam HQ skill is a disclosed OOMOL CLI connector wrapper with read actions and one clearly marked message-sending action that requires user confirmation.

Install only if you intend to let Codex use your OOMOL-connected Roam HQ account. Review any `send_message` payload before approving it, and be aware that first-time setup may require installing the `oo` CLI and signing in to OOMOL.

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 phrase 'Use this skill for ANY Roam HQ request' is overly broad routing guidance that can cause the agent to invoke this skill whenever a task merely mentions Roam, without first checking whether the request is appropriate, safe, or within least-privilege expectations. In this skill, the same interface exposes both read actions and a write action (`send_message`), so over-triggering increases the chance of unintended data access or state-changing operations from ambiguous user prompts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.