financial-report-reader
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a utility for financial report interpretation through a local Python script (
scripts/analyze_financials.py). - [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script to process financial data. The script uses only standard libraries (argparse, json, re, sys, collections) and performs mathematical calculations on structured data. No dangerous command patterns or remote code execution vectors were found.
- [DATA_EXFILTRATION]: No network-capable functions or libraries are used. The script reads an input file and optionally writes an output file, both of which are controlled by the user/agent environment.
- [PROMPT_INJECTION]: The instructions in
SKILL.mdare focused on data processing and report generation. No patterns attempting to bypass safety filters or override system instructions were detected.
Audit Metadata