hugging-face-tool-builder

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow can fetch and parse outsider-authored free text from Hugging Face repositories (e.g., model/dataset card body text via hf download or API responses), which is then ingested into the agent/LLM context for parsing (e.g., frontmatter extraction and card parsing).