The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the bulk_import_clients function, which is designed to process data from external URLs provided via the csv_file_url parameter.
Ingestion points: The csv_file_url parameter in resources/client-management.yaml allows the agent to fetch and ingest untrusted external content.
Boundary markers: The skill definition does not provide boundary markers or instructions to the agent to disregard instructions found within the imported data.
Capability inventory: The skill allows for the creation, modification, and export of sensitive client records and financial statistics, which could be abused if an injection attack succeeds.
Sanitization: There is no evidence of validation or sanitization of the CSV file content before it is processed by the agent.

gestao-clientes