ClawHub
Back to skill

Security audit

Website Generator

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent AnyGen website generator, but it tells the agent to install an additional unreviewed workflow skill with an auto-confirm flag.

Install only if you trust AnyGen, are comfortable using an AnyGen API key, and are comfortable sending website prompts and content to AnyGen. Before allowing the fallback `anygen skill install ... -y` command, review and explicitly approve the additional workflow skill it would add.

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
88% confidence
Finding
The activation text is extremely broad and instructs use for essentially any website-related request, which can cause the skill to trigger in situations where a more appropriate or safer workflow should be used. In an agentic environment, overbroad routing expands the attack surface by sending generic user requests into an external website-generation pipeline and can lead to unintended tool execution or data sharing.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.