explorable-explanation

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation to generate code and interactive content, creating a potential surface for indirect instructions.
  • Ingestion points: The workflow begins by reading user-provided "documentation for the topic" as its primary input (SKILL.md).
  • Boundary markers: There are no specific instructions or delimiters provided to separate external content from the agent's core instructions.
  • Capability inventory: The skill utilizes frontend-design and openai-imagegen tools, and creates subagents to review and modify generated code.
  • Sanitization: No explicit validation or filtering of the source material is described.
  • [EXTERNAL_DOWNLOADS]: The skill references and encourages browsing external educational resources and visual examples from the field of explorable explanations.
  • Fetches design inspiration, vibes, and visual screenshots from Nicky Case's official domain (ncase.me).
  • References design patterns and methodologies from the explorable.es community hub.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:00 PM