tinyworld-island-and-planes

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data that could act as a vector for indirect instructions, specifically through banner messages and layout configurations.
  • Ingestion points: The BANNER_MESSAGES source used for towed banners and island coordinate/layout parameters defined in the skill logic.
  • Boundary markers: No specific delimiters or safety warnings for embedded instructions are mentioned for the processed strings.
  • Capability inventory: The skill interacts with the DOM to set logo-adjacent banners and writes to the world-history snapshot via serializeEditableIslands().
  • Sanitization: The instructions do not specify sanitization or escaping protocols for the content of the BANNER_MESSAGES.
  • [EXTERNAL_DOWNLOADS]: The skill includes a reference to an external social media platform for a sponsor link.
  • Evidence: Mentions a clickable link to https://x.com/Autoincentiv3. This reference targets a well-known service and is used for standard social media redirection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 11:50 AM