ClawHub
Back to skill

Security audit

Moorcheh

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Moorcheh connector that can read and change Moorcheh data, with explicit confirmation requirements for write and delete actions.

Before installing, understand that this skill can operate on your Moorcheh account through OOMOL, including uploading documents and deleting up to 1,000 documents. Use it only with a connected account you trust, and make sure your agent asks for clear confirmation before write or delete actions.

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 instruction to use this skill for "ANY Moorcheh request" is overly broad and can cause the agent to invoke the skill for loosely related or ambiguous tasks without sufficient scoping. In this skill, that matters because the same interface exposes both read and state-changing/destructive actions, increasing the chance of unintended connector use and unnecessary exposure to write-capable operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.