ClawHub
Back to skill

Security audit

DocuGenerate

Security checks across malware telemetry and agentic risk

Overview

This DocuGenerate skill is a coherent connector wrapper with disclosed read, write, and delete actions and explicit confirmation requirements for state-changing operations.

Before installing, understand that this skill can act on your DocuGenerate account, including generating, renaming, and permanently deleting documents. Only approve write or delete commands after checking the exact template, document ID, and payload, and install the oo CLI only from the documented OOMOL source if setup is needed.

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 description is excessively broad: 'Use this skill for ANY DocuGenerate request' can cause the agent to invoke this skill whenever DocuGenerate is merely mentioned, rather than when the user explicitly intends connector-backed actions. That increases the chance of unnecessary access to external data or accidental execution of state-changing operations, especially because the skill exposes read, write, and destructive actions behind a single generic invocation condition.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.