ClawHub
Back to skill

Security audit

Ortto

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Ortto connector that uses the oo CLI for expected read and write operations, with write actions requiring user confirmation.

Install this only if you want an agent to access Ortto through your OOMOL account. Read operations may expose customer/contact data, and merge_people can create or update contacts, so confirm payloads carefully before allowing write actions. Be cautious with the first-time oo CLI installer and authentication steps, and run them only when you actually need to connect the account.

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 manifest description uses an overly broad routing instruction ('ANY Ortto request' and 'Whenever a task involves Ortto'), which can cause an agent to invoke this skill for all Ortto-related tasks without sufficient narrowing or task-specific safety checks. In a skill that supports both read and write operations, this increases the chance of unnecessary delegation, accidental state-changing actions, or bypass of more context-aware handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.