The Agent Skills Directory

[SAFE]: The skill's primary function is text analysis and generation centered on creative writing. It contains no executable scripts, network requests, or attempts to access sensitive system files.
[NO_CODE]: The skill consists entirely of markdown instructions for the AI agent and does not include any accompanying scripts (Python, Node.js, etc.) or binaries.
[PROMPT_INJECTION]: The skill is designed to process external manuscripts via the file:read permission, creating a potential surface for indirect prompt injection. If a processed file contains malicious instructions, the agent might attempt to follow them. However, no specific bypass attempts were detected in the skill itself, and its capabilities are limited to standard file operations.
Ingestion points: Reads chapter text from files specified by the user in SKILL.md commands.
Boundary markers: The instructions do not define clear delimiters or warnings to ignore instructions within the manuscript text.
Capability inventory: The skill uses file:write to save analyzed or rewritten text; it lacks high-risk capabilities like shell access or network communication.
Sanitization: There is no mention of validation or filtering of the manuscript content before it is processed by the model.

first-chapter-hook