The Agent Skills Directory

[SAFE]: The skill operates entirely within the chat context to provide narrative restructuring. It does not require or request access to any restricted tools, system commands, or external network resources.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted user data, such as product drafts and presentation notes.
Ingestion points: User-provided text inputs, drafts, and data described in SKILL.md and README.md examples.
Boundary markers: The skill does not utilize specific delimiters (like triple quotes or XML tags) to isolate user content from system instructions.
Capability inventory: The skill logic is confined to text output; no capabilities for file system access, shell execution, or external network communication are present.
Sanitization: There are no explicit validation or filtering steps for the input data before it is incorporated into the storytelling framework.

storytelling-expert