kmp-compose-design-system

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes external, user-provided files such as PRODUCT.md and docs/design-system.md as context for naming components and defining token values. This ingestion surface is used for legitimate project configuration.
  • Ingestion points: PRODUCT.md and docs/design-system.md located in the project root.
  • Boundary markers: Absent; the files are processed as plain text design context.
  • Capability inventory: The skill includes Python scripts capable of file system modification and code scaffolding within the project directory.
  • Sanitization: Configuration values are extracted via regular expressions or processed directly by the agent context.
  • [EXTERNAL_DOWNLOADS]: The skill references established libraries and vendor-owned resources from well-known platforms.
  • Evidence: Recommends the Pillow library for image color extraction during palette generation.
  • Evidence: Depends on the official detekt-api from Maven Central for static analysis.
  • Evidence: References the author's own GitHub repositories for tailwind-compose and shadcn-compose as complementary tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 09:42 PM