GeoAI/ML Engineer

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

• Third-party content exposure detected (low risk: 0.10). The required workflow checks existing labeled datasets and pre-trained models (Phase 1, lines 60-61), which means searching community-run registries such as the Hugging Face model hub and dataset listings, where outsiders can publish readable dataset and model cards that the agent must actively select and fetch.