courseware-builder

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The generated HTML output references Google Fonts (fonts.googleapis.com) to provide typography for the slide deck. This is a reference to a well-known service used for legitimate UI design purposes and does not pose a security risk.
  • [PROMPT_INJECTION]: The skill includes a design surface for processing user-supplied technical data.
  • Ingestion points: User inputs regarding the topic, actors, and code snippets in Phase 1 and 2.
  • Boundary markers: The instructions mandate a confirmation step where the user reviews the content architecture (Phase 2 Architecture Output) before the HTML is generated.
  • Capability inventory: The agent possesses the capability to generate and save a single, self-contained HTML file.
  • Sanitization: While explicit HTML sanitization instructions are not present, the content is generated into a static template that is executed in the user's browser context.
  • [SAFE]: No malicious patterns, obfuscation techniques, or unauthorized system interactions were detected. The skill's primary purpose is clearly defined and consistent with its implemented logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 02:53 AM
Security Audit — agent-trust-hub — courseware-builder