The Agent Skills Directory

[SAFE]: The skill serves as a standard wrapper for the OpenAI chat completion API, providing structured prompts for business content generation.
[PROMPT_INJECTION]: The skill interpolates user-provided text directly into an LLM prompt in src/index.ts. While this is functional, it constitutes an indirect prompt injection surface if the input is sourced from untrusted external data.
Ingestion points: The idea argument passed via the CLI interface in src/cli.ts.
Boundary markers: User-supplied input is not isolated with specific delimiters or preceded by instructions to ignore embedded commands.
Capability inventory: The skill has local file system write access via fs.writeFileSync in src/cli.ts.
Sanitization: No validation or escaping is applied to the input string before it is sent to the model.
[EXTERNAL_DOWNLOADS]: The skill connects to OpenAI's official API endpoints and is distributed through the npm registry. Both are recognized as well-known and trusted services for software development.

pitch-gen