unsloth-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows explicitly load public, user-contributed datasets from HuggingFace (e.g., references/dataset-formatting.md and references/training-setup.md show load_dataset("yahma/alpaca-cleaned") and load_dataset("mlabonne/guanaco-llama2-1k")), which are untrusted third‑party content that the agent ingests and uses to drive training/behavior, enabling indirect prompt injection risk.