The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the mkdir -p command to create directory structures for organizing generated stories within the docs/stories/ path. This behavior is consistent with the skill's primary function of managing content for an MkDocs textbook.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided inputs, such as scientist names and themes, to generate narratives and file system paths.
Ingestion points: User requests specifying the scientist's name, historical period, and story themes enter the agent context via natural language interaction.
Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the user-provided data.
Capability inventory: The skill possesses the ability to create directories (mkdir) and write markdown files to the local file system.
Sanitization: No explicit sanitization or validation logic is defined for the user-supplied strings before they are used in commands or file content.

story-generator