data-retention-policy
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided data categories and legal bases which could contain malicious instructions.
- Ingestion points:
scripts/retention_schedule.pyreads data from JSON files or standard input. - Boundary markers: The skill instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data it processes.
- Capability inventory: The skill identifies data categories, calculates dates, and flags missing information using a Python script, but lacks network or write capabilities.
- Sanitization: The script performs type checking (e.g., verifying integer months and ISO dates) but does not sanitize string fields like 'category' or 'basis' before outputting them back to the agent.
- [COMMAND_EXECUTION]: The skill uses a local Python helper script (
scripts/retention_schedule.py) to validate retention schedules. - The script relies solely on the Python standard library and does not perform network operations or access sensitive system paths.
Audit Metadata