ClawHub

Flatsome Wordpress

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a coherent Flatsome WordPress page-building guide, but it includes high-impact live-site commands, including permanent page deletion, without enough safeguards.

Review before installing or using on a real WordPress site. Use it on staging first, keep a backup, and instruct the agent not to run WP-CLI mutations, plugin activations, remote media imports, or any `--force` deletion unless you approve the exact site, page ID, title, and command.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger/mapping examples are broad enough that an agent may activate this skill for generic website-building prompts without confirming scope, environment, or user intent. In an agentic context, that can lead to overbroad actions such as site reconfiguration, plugin installation, or content generation on the wrong target system.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill includes a force-delete WP-CLI command (`wp post delete PAGE_ID --force`) with no confirmation, dry-run, backup, or scope checks. In an autonomous or semi-autonomous agent workflow, this creates a real risk of irreversible content loss if the command is applied to the wrong page or environment.

Missing User Warnings

Low
Confidence
88% confidence
Finding
Directly importing media from arbitrary external URLs can leak server/network metadata, trigger unintended outbound requests, and ingest untrusted files into the WordPress media library. In managed or private environments, this also creates privacy and supply-chain risk because the agent may contact third-party hosts without disclosure or validation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal