The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-generated content, which could contain embedded instructions intended to manipulate the agent's behavior.
Ingestion points: The skill reads content from files within the characters/ and worldbuilding/ directories, as well as spec/tracking/timeline.json and chapter text.
Boundary markers: There are no defined delimiters or instructions provided to separate the ingested story data from the agent's operational logic.
Capability inventory: The skill is authorized to use the Read and Grep tools to access and search through project files.
Sanitization: The skill instructions do not specify any validation or sanitization processes for the data being analyzed.

story-consistency-monitor