shiftcare-daily-rundown
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 fetched from ShiftCare API endpoints, including shift details, client names, and staff qualifications. This creates a potential surface for indirect prompt injection if malicious data is stored within the ShiftCare records.
- Ingestion points: Tools such as
list_shifts,list_shift_staffs,list_timesheets, andlist_staff_qualificationsretrieve external data (SKILL.md). - Boundary markers: The skill does not explicitly define delimiters for external data within the output report.
- Capability inventory: The skill is restricted to read-only API calls and does not have capabilities for file writing, network exfiltration, or shell command execution.
- Sanitization: No explicit sanitization or filtering of API-returned strings is mentioned in the instructions.
Audit Metadata