The Agent Skills Directory

[SAFE]: The skill consists of educational templates and code snippets for ETL processes. All identified operations align with the stated purpose of building data pipelines.- [DYNAMIC_EXECUTION]: The provided Python code correctly uses yaml.safe_load() instead of the unsafe yaml.load() for parsing YAML files. This is a security best practice that prevents arbitrary code execution during the ingestion of external configuration or data files.- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes code for network requests (using httpx) and database connectivity (using asyncpg). These are standard capabilities for data extraction in ETL pipelines and are implemented using generic templates without hardcoded credentials or unauthorized destination domains.- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing data from external sources such as APIs and files. While this creates an ingestion surface, the risk is mitigated by the use of normalization, schema validation logic, and the absence of instructions that would cause the agent to execute untrusted content as commands. Ingestion points are located in the FileExtractor, extract_paginated, and extract_from_db functions in SKILL.md. Capabilities include file writing, network requests, and database queries. Sanitization is performed via yaml.safe_load and record validation logic.

data-ingestion-pipeline