The Agent Skills Directory

[SAFE]: The skill's logic is consistent with its stated purpose of generating Yuque reports. It utilizes legitimate MCP tools specifically designed for the Yuque API.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data (document titles, member names, and repository names) from the Yuque environment.
Ingestion points: External data enters the context via yuque_group_doc_stats, yuque_group_member_stats, and yuque_list_repos in SKILL.md.
Boundary markers: None are specified to separate external data from the report generation instructions.
Capability inventory: The skill has the capability to write data back to the platform using yuque_create_doc in SKILL.md.
Sanitization: There is no evidence of sanitization or escaping of the ingested content before it is interpolated into the markdown report template.

group-weekly