The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python utility (webnovel.py) located in the plugin's script directory. This script is used for project root discovery, runtime contract generation, and executing the review pipeline.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) due to its handling of untrusted novel content during the review workflow.\n
Ingestion points: Novel chapter files (e.g., markdown files in the 正文 directory) and the .webnovel/state.json metadata file are read into the context in Steps 3 and 4.\n
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate untrusted chapter content from the reviewer agent's core instructions.\n
Capability inventory: The skill is granted access to high-capability tools including Bash, Write, Edit, and Task, which could be targeted by a successful injection.\n
Sanitization: There is no evidence of content sanitization or validation performed on the chapter text before it is analyzed by the reviewer agent.

webnovel-review