retirement-planning

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/calculate.py) to ensure calculation accuracy. This is the primary mechanism for the skill's functionality and does not involve arbitrary or dangerous commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill supports processing data from external CSV files (e.g., evals/files/retirement_inputs.csv). This ingestion of external data is a standard feature for financial analysis and is handled within the context of mathematical calculations. ● Ingestion points: CSV data files. ● Boundary markers: Not explicitly defined in instructions. ● Capability inventory: Local Python execution for math logic. ● Sanitization: Not implemented in the provided script, but usage is limited to numeric processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:52 AM
Security Audit — agent-trust-hub — retirement-planning