The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (webnovel.py) and Git commands to manage project state.
[COMMAND_EXECUTION]: Employs destructive operations such as git reset --hard and workflow cleanup, which can cause permanent loss of data in the user's local project directory.
[PROMPT_INJECTION]: Identified an Indirect Prompt Injection surface (Category 8). The skill reads workflow state, including previous commands and arguments, from local files (state.json, workflow_state.json).
Ingestion points: Processes data from .webnovel/state.json and workflow_state.json via the webnovel.py script.
Boundary markers: No delimiters or instructions to ignore embedded commands are present when reading data from the state files.
Capability inventory: The skill utilizes Bash for shell command execution and AskUserQuestion for user interaction.
Sanitization: There is no evidence of sanitization or validation for the original_command or original_args variables before they are used to re-trigger tasks in Step 7.
[COMMAND_EXECUTION]: Dynamically assembles and executes agent commands (e.g., /{original_command}) based on unsanitized data retrieved from the project's local state files.

webnovel-resume