huggingface-tool-builder

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path fetches outsider-authored Hugging Face model card text (e.g., hf_model_card_frontmatter.sh downloads README.md from arbitrary model repos via hf download and then parses the README contents into LLM-readable prose/fields), which can include free-form text authored by third parties.