The Agent Skills Directory

[Data Sanitization]: The skill provides the escapeString utility to sanitize string inputs before they are included in generated code. This is a recommended practice to prevent syntax injection or malformed code output.
[Indirect Prompt Injection Surface]: This skill processes external UI specifications to generate code. (1) Ingestion points: The spec object processed in SKILL.md. (2) Boundary markers: No explicit boundary markers or 'ignore' instructions are included in the code snippets. (3) Capability inventory: The skill generates code strings and file objects via functions like serializeProps and CodeGenerator. (4) Sanitization: The skill provides escapeString and serializePropValue to help sanitize and format data correctly during generation.
[Package Reference]: The documentation mentions the @json-render/codegen package. This is a standard library reference for the code generation functionality described and is consistent with the skill's intended purpose.

codegen