sap-hana
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill integrates with SAP S4 HANA and processes external business data such as Sales Orders, Products, and Business Partners.
- Ingestion points: Data enters the agent context through the outputs of
membrane action runandmembrane requestcommands defined inSKILL.md. - Boundary markers: None explicitly defined to separate external data from agent instructions.
- Capability inventory: The skill provides capabilities to list, retrieve, create, and update business records in the connected SAP system via shell commands.
- Sanitization: No explicit sanitization or escaping logic is described in the prompt; the skill relies on the agent's internal guardrails and the platform's API handling.
Audit Metadata