education-learning-material
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches styling and script assets from Google Fonts and jsDelivr (a well-known CDN service) to enable diagrams, charts, and math rendering in the generated HTML.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted
contentand interpolates it into a generated HTML file. While it enablesstrictsecurity settings for the Mermaid diagramming tool, there are no instructions for sanitizing or escaping the general markdown content before it is placed into the HTML document, creating a potential cross-site scripting (XSS) vulnerability. - Ingestion points: The
contentparameter inSKILL.mdused for rendering. - Boundary markers: No delimiters or "ignore" instructions are used for the interpolated data.
- Capability inventory: The skill performs file writes to create
.htmlfiles and defines network requests to be executed by the browser. - Sanitization: No explicit sanitization, escaping, or validation of the input content is documented in the skill instructions.
- [DYNAMIC_EXECUTION]: The skill dynamically generates HTML documents containing JavaScript initialization blocks and library injections that are executed by the user's browser at runtime based on the input data provided.
Audit Metadata