ClawHub
Back to skill

Security audit

Cloudflare Worker

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Cloudflare Worker connector with powerful account actions, but its write and delete operations are clearly labeled and require user approval.

Install this only if you want an agent to manage Cloudflare Workers through OOMOL. Reads can run directly, but writes and deletes affect your Cloudflare account, so check the target account, Worker, payload, and requested action before approving any state-changing command.

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 activation text is extremely broad: it directs use of this skill for ANY Cloudflare Worker request and instead of calling the API directly. That can cause the agent to invoke a high-privilege skill in loosely related contexts without sufficient narrowing, increasing the chance of unintended reads, writes, or destructive operations against a connected Cloudflare account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.