sap-btp-business-application-studio
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the cloning of project repositories from GitHub and the use of Yeoman generators from the npm registry (e.g.,
@sap/fiori). These operations target well-known platforms and official SAP-scoped packages, which is standard practice for the documented development environment. - [COMMAND_EXECUTION]: The skill provides instructions for using standard command-line tools relevant to the SAP BTP environment, including
cf(Cloud Foundry CLI) for deployment,mbt(Cloud MTA Build Tool) for building archives, andcds(SAP Cloud Application Programming Model CLI) for project initialization. These commands are necessary for the development tasks described and do not include any malicious execution patterns. - [INDIRECT_PROMPT_INJECTION]: The skill documents workflows for the agent to help users interact with external data and repositories, which introduces a common surface for indirect prompt injection.
- Ingestion points: Remote Git repositories cloned via the terminal and external OData service definitions explored and integrated via the Service Center (documented in
references/git-operations.mdandreferences/service-center-and-tools.md). - Boundary markers: No specific boundary markers or "ignore embedded instructions" warnings are recommended for the agent when processing these external inputs.
- Capability inventory: The documented environment includes capabilities for file system writes (
cds init,yo), network operations (git clone,cf deploy), and subprocess execution (mbt build). - Sanitization: No specific sanitization or validation protocols are described for the processing of external content within the skill instructions.
Audit Metadata