di-agent-flow-pyflow
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a system for authoring and executing data flows that ingest external data, creating a potential surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via
q.source(),lookup(), and theread_data_previewtool results mentioned in the Output Operations section. - Boundary markers: The skill does not provide specific instructions for using delimiters or boundary markers to isolate untrusted data from processing logic.
- Capability inventory: The skill utilizes
create_pyflow,update_datastage_flow, andcreate_job_runto execute logic and manage data assets on the target engines. - Sanitization: No explicit sanitization or escaping requirements are documented for the agent when handling or displaying content from external data sources.
Audit Metadata