document-design

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interpolate user-provided content into document templates, which is its primary function.
  • Ingestion points: User data is placed into placeholders within HTML templates found in the templates/ directory.
  • Boundary markers: No specific delimiters are used to separate user content from system instructions in the provided documentation.
  • Capability inventory: The skill's operations are limited to local file system writes and browser-based previews. No high-risk capabilities such as arbitrary shell command execution or network exfiltration to unknown domains were detected.
  • Sanitization: The instructions do not explicitly mandate HTML escaping or sanitization for user input.
  • [DYNAMIC_EXECUTION]: The preview utility dynamically loads local JavaScript assets based on the selected template.
  • Evidence: controls/playground-wrapper.html constructs script paths for template maps using a template name parameter. These loads are restricted to the local playground-controls/template-maps/ directory within the skill's own file structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — document-design