ingest-figma

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design metadata and style definitions from Figma's official API (api.figma.com). This interaction is consistent with the skill's stated purpose of ingesting design tokens.
  • [COMMAND_EXECUTION]: Utilizes curl to interact with the Figma REST API and test to verify environment variables. The commands are scoped to specific API endpoints.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Figma API JSON responses and user-provided SVG files in the artifacts/ingested/ directory.
  • Boundary markers: None explicitly defined for ignoring instructions embedded in design layer names or metadata.
  • Capability inventory: File system read/write access and the ability to execute curl commands.
  • Sanitization: The skill uses targeted parsing logic to extract specific technical attributes (e.g., color hex codes, font family, font size) rather than processing text fields as instructions, which reduces the risk of unintended command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 03:01 PM