staff-scheduling

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external workforce management systems (UKG, Workday, union agreements), which creates a surface for indirect prompt injection. Ingestion points: WFM configuration files, payroll export formats, and union collective bargaining agreements. Boundary markers: Absent. Capability inventory: Local file system writes (docs/ and telemetry) and execution of downstream skills like /demand-forecasting. Sanitization: Absent.
  • [DATA_EXFILTRATION]: The skill is designed to discover and analyze sensitive infrastructure including payroll integrations, time and attendance systems, and employee data. While it performs local file operations and reporting, no evidence of unauthorized network exfiltration was detected.
  • [COMMAND_EXECUTION]: The skill performs local file writes to create analysis reports and telemetry logs, which is consistent with its stated primary purpose as an audit tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — staff-scheduling