statement-preparation

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs financial statement preparation using accounting logic and a local Python script for calculations. All components trace back to the local skill directory with no external dependencies or network operations detected.
  • [DATA_INGESTION]: The skill processes user-provided trial balance data and CSV files (e.g., evals/files/movement_data.csv). While this constitutes a data ingestion surface for indirect prompt injection, the skill's capabilities are limited to mathematical calculations within a local script, presenting no significant security risk.
  • [COMMAND_EXECUTION]: The skill references a local Python script (scripts/calculate.py) for math operations. This is a best-practice approach for ensuring numerical precision in financial reporting and does not involve execution of untrusted remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:51 AM
Security Audit — agent-trust-hub — statement-preparation