huggingface-tool-builder

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow fetches Hugging Face model cards/README.md from arbitrary third-party repositories (via hf download ... README.md in hf_model_card_frontmatter.sh and via curl of https://huggingface.co/$model_id/raw/main/README.md in hf_model_papers_auth.sh), and that fetched free-form markdown text is then parsed/processed and thus becomes LLM-readable context (indirect prompt injection risk).