gsp-typography

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes Google Fonts for web font imports and references typescale.com to allow users to preview typography ratios. These are well-known services appropriately used for the skill's intended purpose.
  • [PROMPT_INJECTION]: The skill supports an enrichment mode that reads existing project files to extract and enhance font settings, creating a surface for indirect prompt injection.
  • Ingestion points: Reads existing files at {BRAND_PATH}/identity/typography.md.
  • Boundary markers: No explicit delimiters or ignore-instructions warnings are specified for the read content.
  • Capability inventory: The skill has access to Bash, Read, and Write tools to modify the project environment.
  • Sanitization: No explicit sanitization or validation of the ingested typography content is described.
  • [COMMAND_EXECUTION]: The skill's architecture involves dynamic path construction to load internal logic files from the domains/ directory based on input arguments. This loading is scoped to the skill's own directory, which is a standard pattern for modularizing complex agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 04:01 AM