The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run local utility scripts (webnovel.py) for workflow management and data indexing.
Evidence: SKILL.md contains multiple bash commands executing python "${SCRIPTS_DIR}/webnovel.py" --project-root "${PROJECT_ROOT}" index save-review-metrics --data '@review_metrics.json'.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it processes user-controlled novel chapters while possessing significant tool capabilities like file editing and command execution.
Ingestion points: The novel chapter text processed by checker sub-agents and the .webnovel/state.json project configuration file.
Boundary markers: There are no explicit delimiters or instructions to the agents to ignore potential commands embedded within the chapters.
Capability inventory: The skill has access to powerful tools including Bash, Write, Edit, and Read.
Sanitization: Novel chapter content is not sanitized or validated for malicious instructions before being passed to sub-agents for review.

webnovel-review