alterlab-transformers

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs loading models and datasets from the public Hugging Face Hub (e.g., SKILL.md authentication and from_pretrained calls in references/models.md and references/generation.md) and shows pipelines accepting external URLs and datasets.load_dataset (references/pipelines.md and references/training.md), so it ingests untrusted, user-contributed third-party content that can materially change agent behavior.