ClawHub
Back to skill

Security audit

Dokploy

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Dokploy connector with powerful account actions, but it scopes execution through the oo CLI and requires confirmation for state-changing and destructive operations.

Install this only if you want an agent to manage Dokploy through your OOMOL account. Treat write and destructive actions as production-impacting: confirm the exact target, payload, and effect before approving them, and be aware that read actions can expose Dokploy configuration, logs, repositories, and deployment information visible to the connected API key.

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 text is extremely broad: 'Use this skill for ANY Dokploy request' and 'Whenever a task involves Dokploy, use this skill instead of calling the API directly.' This can cause the agent to invoke the skill for any mention of Dokploy, including ambiguous or low-confidence contexts, increasing the chance of unintended connector use and state-changing operations in an environment with many write and destructive actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.