group-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Yuque documents which could potentially contain malicious instructions intended to manipulate the agent's categorization or summarization logic.
- Ingestion points: Document titles and metadata are retrieved via
yuque_get_toc(Step 2b), and document content is retrieved viayuque_get_doc(Step 4). - Boundary markers: The workflow does not specify the use of delimiters (e.g., XML tags or triple quotes) or 'ignore' instructions when processing document content for summaries or categorization.
- Capability inventory: The agent has the capability to write documents back to the Yuque environment using
yuque_create_doc(Step 6). - Sanitization: There is no explicit sanitization or filtering of the retrieved document content before it is processed by the model to generate the onboarding guide.
Audit Metadata