The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute multiple Python scripts with arguments parsed from user-provided data. This is the intended operation of the skill but constitutes a controlled command execution surface.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the external files it processes. Ingestion points: Data is read from user-provided files in scripts/procesar_facturas.py, scripts/generar_libro.py, and scripts/procesar_stripe.py. Boundary markers: No specific delimiters or "ignore previous instructions" warnings are utilized when the agent presents data from these files. Capability inventory: The skill can execute local Python scripts and generate new CSV or JSON ledger files. Sanitization: Numeric fields are handled via the Decimal library, but string-based fields from the CSV rows are not sanitized before they are processed by the scripts or interpreted by the agent.\n- [EXTERNAL_DOWNLOADS]: The script scripts/procesar_stripe.py imports the urllib.request library. While this library is not currently used in the script's logic, its inclusion in a utility meant for local financial data processing is an unnecessary capability.

gestor-autonomos