sap-btp-master-data-integration

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to process and integrate enterprise master data, which presents a surface for indirect prompt injection if malicious instructions are embedded in the source systems.
  • Ingestion points: Data enters the agent's context through SAP MDI SOAP and REST API responses (e.g., Business Partner replication records) as documented in soap-api-reference.md and features-complete.md.
  • Boundary markers: The instructions do not specify the use of delimiters or specific commands for the agent to ignore instructions embedded in the master data fields.
  • Capability inventory: The agent can configure distribution models, manage connectivity between critical SAP systems (S/4HANA, Ariba, etc.), and set up authentication via OAuth2 or mTLS.
  • Sanitization: The documentation notes that MDI performs schema validation against the SAP One Domain Model (ODM), but it does not specify sanitization or filtering of natural language content within the data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:16 AM
Security Audit — agent-trust-hub — sap-btp-master-data-integration