ClawHub

Generate responsive HTML pages suitable for reporting, supporting resizing and screenshot capture.

Security checks across malware telemetry and agentic risk

Overview

This report generator does what it claims, but it can render unescaped user content as local HTML in a browser, creating a real script-execution risk.

Install only if you will use it with trusted report content or can update it to HTML-escape all user-supplied fields before rendering. Be aware it creates local HTML files and asks the agent to open them in a browser for screenshots.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to execute a local Python script and write generated output to workspace/reports, which implies shell execution and file-write capability without any declared permissions or constraints. This weakens security review and increases the chance that a broadly invocable skill could be used to perform unintended local actions or process adversarial input through tooling the platform did not explicitly authorize.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description says to invoke the skill whenever a user wants to create a report, slide, or summary card from raw content, which is broad enough to match many ordinary requests. Because the skill also drives shell execution, file generation, and browser-based rendering, overly broad routing can cause these higher-risk actions to run in contexts where they are unnecessary or where untrusted content is being handled automatically.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal