generate-cds-analytical-query

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses high-privilege tools such as SAPQuery, SAPWrite, and SAPActivate to perform administrative tasks within the SAP environment, including verifying system versions and deploying new data definitions.
  • [INDIRECT_PROMPT_INJECTION]: The skill's design creates an attack surface for indirect prompt injection by processing untrusted data from user descriptions and system metadata to generate executable code.
  • Ingestion points: User-provided business descriptions and cube metadata retrieved via SAPRead and SAPSearch.
  • Boundary markers: The skill does not provide specific delimiters or instructions for the agent to ignore commands embedded in the processed data.
  • Capability inventory: The skill has access to tools for writing (SAPWrite), activating (SAPActivate), and querying (SAPQuery) the SAP system.
  • Sanitization: No validation or sanitization of the input data is performed before it is interpolated into code templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:09 AM
Security Audit — agent-trust-hub — generate-cds-analytical-query