sap-clean-core-atc
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted custom code from SAP packages to perform its audit functions. This creates a potential surface where malicious instructions embedded in the analyzed code could attempt to influence the agent's output.
- Ingestion points: Custom ABAP code and metadata are retrieved using
SAPReadandSAPContextas described inSKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the ingested code content.
- Capability inventory: The skill utilizes
SAPRead,SAPSearch,SAPContext,SAPDiagnose, andsap_get_object_detailsto interact with the system and documentation. - Sanitization: There is no evidence of specific sanitization or filtering of the source code before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references a repository from a well-known service for official SAP release state data (GitHub repository
SAP/abap-atc-cr-cv-s4hc). This is a legitimate source for the technical metadata required for the skill's primary purpose.
Audit Metadata