social-spotify-card

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's example code fetches resources from well-known services to handle styling and typography, including Tailwind CSS (cdn.tailwindcss.com) and Google Fonts (fonts.googleapis.com).
  • [PROMPT_INJECTION]: The skill provides a template that ingests untrusted user content (such as song titles, artist names, and descriptions) and embeds it directly into an HTML structure, creating an indirect prompt injection surface.
  • Ingestion points: Music and podcast metadata provided by the user, as identified in the SKILL.md template logic.
  • Boundary markers: The template lacks explicit delimiters or instructions to isolate user-supplied strings from the surrounding HTML and CSS code.
  • Capability inventory: The skill is restricted to generating visual UI components and does not have access to command execution, sensitive files, or network exfiltration tools.
  • Sanitization: There are no instructions for sanitizing or escaping the user-provided text before it is inserted into the output card, which could allow structural interference if the content is not handled correctly by the rendering agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 02:30 AM