The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection due to its core functionality of processing external Figma design data.
Ingestion points: Figma node details and design metadata are retrieved via the figma_get_node_details tool.
Boundary markers: Prompt templates in references/prompts/ do not use explicit delimiters or instructions to ignore embedded commands in the design metadata.
Capability inventory: The skill orchestrates agents capable of writing code to the local file system and executing terminal commands for project testing and setup.
Sanitization: No explicit validation or filtering of design data is documented before processing.
[EXTERNAL_DOWNLOADS]: The documentation references installation of standard development dependencies like playwright, vitest, and class-variance-authority. These are legitimate tools for the skill's purpose and are downloaded from well-known public registries.
[SAFE]: No malicious obfuscation, unauthorized data exfiltration, or persistence mechanisms were detected. The skill follows best practices for secret management by advising users to store API tokens as environment variables rather than hardcoding them.

figma-to-code