b2c-custom-job-steps
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for processing potentially untrusted data and performing sensitive operations, which establishes an indirect prompt injection surface.
- Ingestion points: Data is ingested from the platform database via
dw/catalog/ProductMgr,dw/order/OrderMgr, anddw/customer/CustomerMgr(referenced inreferences/CHUNK-ORIENTED.md), as well as from external files usingdw/io/FileReader(referenced inreferences/TASK-ORIENTED.md). - Boundary markers: The provided code templates do not include explicit delimiters or instructions to the agent to ignore embedded commands within the processed data.
- Capability inventory: The skill guides the use of powerful capabilities including file system writing via
dw/io/FileWriterand external network communication viadw/net/HTTPClient,dw/net/FTPClient, anddw/net/SFTPClient. - Sanitization: While basic CSV escaping is demonstrated in the
Product Export Example, the templates lack robust validation or sanitization of ingested content before it is passed to network or file-system tools.
Audit Metadata