shiftcare-staff-compliance-check
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data such as staff names and qualification titles retrieved from the ShiftCare API. This data is interpolated into reports, creating a surface where malicious instructions in the source database could potentially influence the agent's behavior.
- Ingestion points:
list_staffandlist_staff_qualificationsinSKILL.md. - Boundary markers: The skill does not define explicit delimiters or 'ignore' warnings for the data fields it processes.
- Capability inventory: The skill is limited to read-only MCP tool calls (
list_staff,list_staff_qualifications,list_qualifications,list_qualification_categories). - Sanitization: No explicit sanitization or escaping of external content before interpolation is mentioned.
Audit Metadata