The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from external Yuque documents through the yuque_get_doc tool, which can lead to indirect prompt injection if those documents contain malicious instructions.
Ingestion points: Untrusted document data enters the agent context via the yuque_get_doc tool described in Step 5 of SKILL.md.
Boundary markers: No explicit delimiters or 'ignore' instructions are provided to separate fetched document content from the agent's core instructions.
Capability inventory: The skill utilizes the yuque_list_repos, yuque_search, and yuque_get_doc tools to interact with repository data.
Sanitization: The instructions do not define any sanitization, escaping, or validation steps for the content retrieved from documents before it is synthesized into the user response.

group-search