poster-hero

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches styling and assets from well-known technology services.
  • Loads the Tailwind CSS library via the official CDN at cdn.tailwindcss.com.
  • Imports web fonts from the Google Fonts service (fonts.googleapis.com).
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external text to generate content.
  • Ingestion points: User-provided marketing copy, headlines, and feature descriptions are ingested to populate the HTML templates described in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt templates.
  • Capability inventory: The skill generates HTML and SVG code which is rendered by the agent or the user's browser.
  • Sanitization: No validation or sanitization of the input text is implemented before it is interpolated into the HTML output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 12:15 PM
Security Audit — agent-trust-hub — poster-hero