yuque-personal-style-extract
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Yuque documents to perform writing style analysis, which creates a surface for indirect prompt injection.
- Ingestion points: The
yuque_get_doctool is used in Step 1 to read the full content of documents from the user's or searched repositories. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the document content as data only or to ignore any embedded instructions within the text.
- Capability inventory: The skill uses
yuque_search,yuque_get_doc, andyuque_list_repostools. These are limited to searching and reading document metadata and content from the Yuque platform. - Sanitization: There are no sanitization or filtering steps defined to process the document content before it is analyzed by the agent.
Audit Metadata