The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes document content from a personal Yuque account, creating a surface for indirect prompt injection where instructions embedded in documents could influence agent behavior.
Ingestion points: Document content is retrieved via the yuque_get_doc tool in Step 4.
Boundary markers: The workflow lacks explicit delimiters or instructions to treat document content as untrusted data.
Capability inventory: The skill uses yuque_search and yuque_get_doc to access and read documents.
Sanitization: No sanitization or filtering is applied to the retrieved document text before synthesis.

personal-search