The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from multiple project files, creating a surface for indirect prompt injection.
Ingestion points: The skill reads from story.md, chapters/_index.md, plot/_index.md, plot/timeline.md, and files within the plot/arcs/, characters/, and locations/ directories.
Boundary markers: There are no specified boundary markers or instructions to ignore potential commands within the story files when they are loaded into the context.
Capability inventory: The skill is capable of reading and writing Markdown files within the project structure. It does not possess capabilities for network communication, shell command execution, or dynamic code evaluation.
Sanitization: The skill does not perform sanitization or validation of the content retrieved from the story files before use.

chapter-writing