json-to-html-table-with-lit

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install dependencies using npm i lit and npm i -D @types/node from the official NPM registry.
  • [DATA_EXFILTRATION]: The Lit component performs network requests using fetch(this.src) to retrieve data. The documented example targets jsonplaceholder.typicode.com, which is a well-known service for placeholder data used in development and testing.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a component that renders content fetched from a remote URL or an inline script tag into an HTML table, creating a surface for indirect instructions if the data source is untrusted.
  • Ingestion points: The component reads data from a URL provided in the src attribute or from a <script type="application/json"> element in SKILL.md.
  • Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are included in the component logic.
  • Capability inventory: The component performs network fetch operations and renders the resulting data into the DOM.
  • Sanitization: The component utilizes Lit's html template literal, which provides default protection against XSS by escaping interpolated values when rendered as text content.
  • [SAFE]: No malicious behavior, obfuscation, or persistence mechanisms were detected. The skill represents normal educational functionality authored by the vendor.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 08:22 PM