finance-skills

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides seven Python automation tools (e.g., ratio_calculator.py, dcf_valuation.py, metrics_calculator.py) designed to be executed via the CLI. These scripts are self-contained and rely exclusively on the Python standard library (math, statistics, json, argparse).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied financial data to generate reports and advice.
  • Ingestion points: Data enters the system via raw business numbers provided by the user in the chat or through JSON files passed to the scripts.
  • Boundary markers: Explicit boundary markers are not implemented in the prompt templates; however, the scripts are mathematical in nature and do not execute external logic based on input strings.
  • Capability inventory: Subprocess calls are limited to the execution of the included Python scripts. There are no network operations, file-write operations (outside of standard output), or privilege escalation attempts.
  • Sanitization: Input data is processed as numeric values or parsed as JSON using standard libraries, which naturally limits the risk of instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:33 PM
Security Audit — agent-trust-hub — finance-skills