The Agent Skills Directory

[COMMAND_EXECUTION]: The skill dynamically generates and executes JavaScript code using the figma_execute and use_figma tools. This is used as a read-only escape hatch to fetch missing facts directly from Figma when the local cache is incomplete.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its ingestion of external data. • Ingestion points: The skill reads data from {cachePath}/{componentSlug}-_base.json and accepts user-provided optionalContext. • Boundary markers: No explicit delimiters or instruction-bypass warnings are mentioned for these inputs. • Capability inventory: The skill has the ability to read and write local files and execute code within the Figma environment via MCP tools. • Sanitization: No sanitization or validation of the input content is described before it is used to drive logic or script generation.

extract-api