data-ingestion-pipeline

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes an API extractor (extract_paginated using httpx.get against a provided base_url) and the pipeline.run calls extractor.extract(source), which shows the skill fetches and ingests arbitrary external API/web content that the agent processes and uses to drive validation, transformation, deduplication, and loading decisions.