Generate Annual Schedule

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the openpyxl Python library to handle Excel files. This is a well-known, legitimate package for spreadsheet manipulation.
  • [COMMAND_EXECUTION]: The skill executes a local Python script (generate_annual_schedule.py) to perform its scheduling logic. This is an internal component of the skill and does not involve executing untrusted commands.
  • [DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were detected. The skill reads local files and writes output to the local file system as intended.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (Excel spreadsheets and markdown school calendars).
  • Ingestion points: Reads .xlsx files via openpyxl and .md files via local file read.
  • Boundary markers: None explicitly used for external text, though data is primarily parsed for dates and provider names.
  • Capability inventory: File write access and local Python execution.
  • Sanitization: Dates and numeric values are validated and parsed. Excel formulas are generated using fixed templates which mitigates formula injection risks. The risk of indirect prompt injection is assessed as low due to the structured nature of the data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 12:01 AM
Security Audit — agent-trust-hub — Generate Annual Schedule