yuque-group-onboarding-guide
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by scanning Yuque knowledge bases and reading document contents.
- Ingestion points: The skill uses
yuque_get_tocandyuque_get_docto retrieve document titles, hierarchies, and body content from external repositories. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within the titles or bodies of the documents being summarized.
- Capability inventory: The skill possesses both read capabilities (listing repos, TOCs, and members) and write capabilities (creating new documents via
yuque_create_doc). - Sanitization: The workflow lacks explicit validation or sanitization of the retrieved document data before it is interpolated into the final onboarding guide template.
Audit Metadata