frame-light-leak-cinema

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external resources for visual rendering. Specifically, example.html loads the Tailwind CSS framework from https://cdn.tailwindcss.com and multiple font families from https://fonts.googleapis.com. These are recognized well-known services.
  • [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest untrusted user data into its output templates, representing an attack surface. 1. Ingestion points: SKILL.md instructs the agent to use user-provided titles and derive metadata (year, location, chapter) from user content. 2. Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the user data. 3. Capability inventory: The skill is capable of generating and rendering HTML and CSS. 4. Sanitization: No explicit validation, escaping, or sanitization steps are defined for the user-supplied content before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:57 PM
Security Audit — agent-trust-hub — frame-light-leak-cinema