The Agent Skills Directory

SAFE (SAFE): No malicious patterns or security vulnerabilities were detected. The skill primarily serves as a template repository for common data engineering tasks.- Indirect Prompt Injection (LOW): The skill is designed to ingest data from external sources (APIs, S3, CSV), which creates a theoretical surface for indirect prompt injection. However, this is the primary purpose of the skill, and the provided patterns include mitigation strategies such as signature verification and data validation.- External Downloads (SAFE): The skill references installation of well-known packages (e.g., polars, dlt, boto3) from standard registries and includes a link to the official Airbyte repository. These sources are considered trusted.- Dynamic Execution (SAFE): The utility script generate_dlt_pipeline.py generates boilerplate Python code based on templates. This is a standard scaffolding tool and does not involve runtime execution of untrusted data.

ingesting-data