The Agent Skills Directory

[SAFE]: The skill operates entirely within the Yuque ecosystem using the yuque-mcp server. It performs standard read and write operations on the user's own documents. No unauthorized network requests, suspicious downloads, or credential harvesting patterns were observed.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze document content, which represents a surface for indirect prompt injection.
Ingestion points: Writing samples are retrieved via yuque_get_doc in Step 1 of the workflow.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed documents.
Capability inventory: Across SKILL.md, the skill utilizes yuque_list_books, yuque_list_docs, yuque_get_doc, yuque_search, and yuque_create_doc to manage content.
Sanitization: There is no explicit sanitization or filtering of the document body before it is processed by the agent for analysis.

style-extract