generate-rap-service

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language descriptions from the user to generate technical source code and system artifacts.
  • Ingestion points: The user-provided "business object description" serves as the primary input for generating the artifact stack (defined in the 'Input' section of SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or sanitization rules for the interpolation of user-supplied field names or labels into the generated DDL or ABAP code.
  • Capability inventory: The skill uses SAPWrite to create artifacts and SAPActivate to activate code and publish services on the target SAP system.
  • Sanitization: No explicit sanitization or escaping is described; the skill relies on the model's generation logic to produce valid and safe code.
  • [DYNAMIC_EXECUTION]: The skill dynamically constructs and writes ABAP source code and CDS definitions at runtime using predefined templates and metadata derived from user input.
  • The SAPWrite tool is used to perform batch creation of multiple executable artifacts (Classes, BDEFs, SRVDs) which are then activated in the system environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 12:04 PM