sap-fiori-add-visual-filter
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface where user-supplied inputs (like entity and field names) are interpolated into code templates. This is an expected part of the skill's functionality as a development assistant and is assessed as safe.\n
- Ingestion points: Gathering user inputs for 'Entity', 'Dimension field', and 'Measure field' (SKILL.md).\n
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions are included in the code templates.\n
- Capability inventory: The skill modifies manifest files (JSON), metadata (XML), and source code (CDS, ABAP).\n
- Sanitization: The instructions do not define validation or escaping logic for the interpolated user strings.
Audit Metadata