The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process novel chapters and related configuration files, which are untrusted external inputs. This creates a standard surface for indirect prompt injection if the audited text contains malicious instructions. However, the risk is minimal as the skill only performs analysis and reporting.
Ingestion points: Reads novel chapter text and context files from the 设定/ and summary/ directories as defined in the workflow.
Boundary markers: The skill does not explicitly define delimiters or specific 'ignore embedded instructions' warnings for the input text.
Capability inventory: The skill utilizes file read capabilities for context gathering and outputs a structured Markdown report.
Sanitization: No specific sanitization, escaping, or validation of the input text is described in the workflow.

novel-review