adding-model-support

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly requires fetching and reading HuggingFace model links and their public config.json / checkpoints (e.g., "Get the HF model link" and "Read the model's config.json from HuggingFace", plus example commands like AutoBridge.from_hf_pretrained and convert_checkpoints.py) — these are untrusted, user-generated third-party sources whose contents directly determine bridge/provider mappings and conversion actions.