present

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill generates HTML that includes links to the reveal.js CSS and JavaScript files hosted on JSDelivr (cdn.jsdelivr.net), a well-known and trusted Content Delivery Network.
  • [PROMPT_INJECTION]: The skill displays an attack surface for indirect prompt injection through the processing of untrusted markdown documents. * Ingestion points: Reads content from source documents via the document-path argument (SKILL.md). * Boundary markers: The skill does not define specific markers or instructions to disregard potential commands found within the source documents. * Capability inventory: Performs file read operations and file write operations for HTML generation (SKILL.md). * Sanitization: There is no evidence of content sanitization or output escaping to prevent the execution of scripts embedded in the source content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:57 PM