peft-fine-tuning

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

• Third-party content exposure detected (high risk: 0.90). The skill's Quick start and examples explicitly load public models and datasets from Hugging Face (e.g., AutoModelForCausalLM.from_pretrained("meta-llama/...") and load_dataset("databricks/databricks-dolly-15k")) and link to the HuggingFace/GitHub hubs, meaning it fetches and ingests untrusted, user-contributed third‑party content that will be read and used in training/inference and could materially influence behavior.