The Agent Skills Directory

[SAFE]: Comprehensive review of all 7 Python scripts (ratio_calculator.py, dcf_valuation.py, budget_variance_analyzer.py, forecast_builder.py, metrics_calculator.py, quick_ratio_calculator.py, and unit_economics_simulator.py) confirms they use only Python standard libraries (math, statistics, json, argparse, sys). No external dependencies are required or used.
[COMMAND_EXECUTION]: Scripts use argparse for command-line interaction and perform local calculations only. There are no instances of subprocess.run, os.system, eval, or exec that could be used for arbitrary command execution.
[DATA_EXFILTRATION]: No network communication modules (such as requests, urllib, or socket) are present in the code. The scripts process data provided locally via JSON files and output results to the console.
[PROMPT_INJECTION]: The markdown instructions in SKILL.md and related documentation are focused on financial workflows and tool usage. No attempts to bypass safety filters or override agent behavior were detected.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in any of the 25 files. The skill correctly instructs users to provide data through local JSON files.
[OBFUSCATION]: All code and instructions are provided in clear text with no evidence of Base64 encoding, zero-width characters, or homoglyph attacks.

finance-skills