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 instructs loading public models and datasets from Hugging Face (e.g., AutoModelForCausalLM.from_pretrained("meta-llama/...") and dataset = load_dataset("databricks/databricks-dolly-15k")) and links to huggingface.co, which are open/public, user-contributed sources that the agent would ingest and thus could carry untrusted, user-generated content enabling indirect prompt injection.