visual-design

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied strings for image generation and presentation content, representing a standard injection surface.
  • Ingestion points: User-provided prompts in CLI arguments (e.g., nanobanana generate) and markdown content for Slidev.
  • Boundary markers: None defined within the skill's instructions.
  • Capability inventory: Network capabilities (Gemini API) and file system writes (output directory).
  • Sanitization: Relies on the safety filters of the underlying Gemini models and Slidev rendering.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading the nanobanana CLI and Slidev tools.
  • Fetches the nanobanana binary from the vendor's official GitHub releases.
  • Installs Slidev components from the official npm registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:38 PM
Security Audit — agent-trust-hub — visual-design