sustainability-fulltext-fetch

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests external, potentially untrusted web content: it calls OpenAlex and Semantic Scholar APIs (fetch_api_metadata / fetch_openalex / fetch_semantic_scholar) and falls back to fetching and extracting full text from arbitrary canonical_url or url values via fetch_html and build_extract_result_from_html (trafilatura or HTML parser), so it will read/interpret third‑party webpages as part of its workflow.