hugging-face-tool-builder

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when references/hf_model_card_frontmatter.sh uses hf download "$model_id" README.md to fetch a model card’s README.md from the Hugging Face repo (README content is authored by third parties) and then parses that downloaded text as YAML frontmatter into the script’s LLM-relevant output.