ppt-generator

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's HTML template and design specifications reference resources from well-known services. It fetches the TailwindCSS framework from a ByteDance CDN (lf26-cdn-tos.bytecdntp.com) and loads fonts from Bilibili's CDN (s1.hdslb.com) and the Loli.net mirror.
  • [PROMPT_INJECTION]: The skill processes untrusted user-supplied lecture notes and transforms them into executable HTML content, creating an attack surface for indirect prompt injection.
  • Ingestion points: User lecture notes are read in the first step of the generation process as documented in SKILL.md.
  • Boundary markers: There are no specific delimiters or instructions to treat user input as data only or to ignore embedded instructions within the notes.
  • Capability inventory: The skill generates a standalone HTML file containing CSS and JavaScript intended for browser execution.
  • Sanitization: The instructions do not specify any methods for escaping or validating the user's text before it is interpolated into the HTML/JavaScript context of the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:13 PM