group-onboarding
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for Indirect Prompt Injection because it processes content from external Yuque documents.
- Ingestion points: Untrusted document content and tables of contents are retrieved from Yuque knowledge bases using the
yuque_get_docandyuque_get_toctools. - Boundary markers: There are no boundary markers or explicit instructions to the agent to treat the retrieved content as untrusted or to ignore embedded instructions.
- Capability inventory: The agent has the capability to create new documents (
yuque_create_doc) and list team members (yuque_group_members), which could be misused if an injection occurs. - Sanitization: The retrieved text is summarized and formatted into a new document without any validation or sanitization of the input data.
Audit Metadata