The Agent Skills Directory

[SAFE]: The skill's source code and configuration files contain no malicious patterns, obfuscation, or unauthorized data access attempts. The functionality matches the described purpose.
[EXTERNAL_DOWNLOADS]: The skill downloads its core logic from the official NPM registry and communicates with OpenAI's API. These are well-known technology services and are expected for the tool's primary function.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it interpolates user-supplied color strings directly into the LLM prompt without sanitization or protective boundary markers.
Ingestion points: CLI arguments collected in src/cli.ts and joined in src/index.ts as the colors array.
Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the system or user prompts.
Capability inventory: The skill has file system write capabilities via fs.writeFileSync in src/cli.ts to save generated themes.
Sanitization: No validation or escaping is performed on the input color strings before sending them to the model.

theme-gen