sfcc-business-manager
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a pattern for ingesting external data files that are then utilized in network operations, creating an attack surface for indirect prompt injection.
- Ingestion points: Local XML files (catalog.xml, inventory.xml, pricebook.xml) are read from the filesystem using
fs.readFileSyncas demonstrated in theimport-runner.jsscript examples. - Capability inventory: The skill uses
fetchto execute network operations against remote Salesforce Commerce Cloud instances, specifically through WebDAV for file uploads and the Jobs API for execution. - Boundary markers: There are no explicit delimiters or instructions provided to isolate or disregard potentially malicious instructions embedded within the ingested XML content.
- Sanitization: The skill does not describe any sanitization or validation of the ingested XML data beyond general compliance with SFCC XSD schemas.
Audit Metadata