yuque-personal-note-refine
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from Yuque notes, which constitutes untrusted data that could influence the agent's behavior.
- Ingestion points: The
yuque_get_doctool is used to read raw document content into the agent's context in Step 2. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing note content.
- Capability inventory: The skill has the ability to write or modify data via the
yuque_create_docandyuque_update_doctools. - Sanitization: There is no mention of sanitizing or escaping the text retrieved from documents before it is analyzed and restructured by the agent.
Audit Metadata