skills/wkentaro/skills/to-html/Gen Agent Trust Hub

to-html

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to offer the user the command xdg-open to view generated HTML files. While the skill specifies not to open them unprompted, this provides a pathway for shell command execution.
  • [COMMAND_EXECUTION]: The HTML template in FORMAT.md configures the Mermaid diagramming library with securityLevel: "loose". This setting is a known security risk that allows HTML and script tags to be executed within diagram labels. Since the skill is intended to render arbitrary content (e.g., bug reports, external data), this creates a Cross-Site Scripting (XSS) vulnerability for the user opening the generated file.
  • [EXTERNAL_DOWNLOADS]: The skill's HTML template fetches external assets from well-known and established services:
  • It loads Tailwind CSS from https://cdn.tailwindcss.com.
  • It imports the Mermaid library from https://cdn.jsdelivr.net.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 02:30 AM
Security Audit — agent-trust-hub — to-html