mlx

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly loads and converts models from the public Hugging Face hub (e.g., load("mlx-community/...") and CLI convert --hf-path), meaning it fetches and ingests third‑party, user‑provided model artifacts which are then executed to generate outputs and can therefore introduce arbitrary instructions that influence agent behavior.