html-coder

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill generates HTML and JavaScript documents based on user-provided input, which creates a potential surface for indirect instructions to be processed when the generated content is previewed or executed in a browser environment.
  • Ingestion points: The agent ingests user-supplied topics and content requirements to generate specific project subdirectories and HTML files (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to prevent the agent from following instructions that may be embedded in the user-provided content.
  • Capability inventory: The skill utilizes filesystem tools to write files and invokes the open_workspace_preview tool to render the generated project (SKILL.md).
  • Sanitization: Absent. No explicit requirements for escaping, validating, or filtering user-provided text before interpolation into HTML templates are defined in the instructions.
  • [EXTERNAL_DOWNLOADS]: The documentation and reference guides include numerous examples of integrating external resources from well-known and industry-standard services.
  • Evidence: The skill provides examples of using CDNs such as jsDelivr, unpkg, jQuery, and Tailwind CSS, as well as Google Fonts, to demonstrate standard web development practices (references/add-css-style.md, references/add-javascript.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:44 AM