The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform local operations. It executes cat to retrieve content from local reference documents and project state files (e.g., .webnovel/state.json). It also executes a local Python utility script (webnovel.py) located in the plugin's script directory to resolve project paths and perform status analysis.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-generated story content and project settings, which constitutes a surface for indirect prompt injection. Ingestion points: Reads project files including state.json, character cards, and setting files located within the user's workspace. Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from interpreting instructions embedded within the story data. Capability inventory: The agent has access to Bash, Read, and Grep tools while processing this data. Sanitization: No explicit sanitization or filtering of the project data is performed before it is presented to the agent.

webnovel-query