scholar-search

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

• Third-party content exposure detected (high risk: 0.70). The skill directly fetches and ingests public, third‑party scholarly content from api.openalex.org (see SKILL.md "Internet access to api.openalex.org" and scripts/scholar_search.py's API_BASE/_http_get_json and reconstruct_abstract), reconstructs and returns abstracts and metadata which the agent is expected to read and use for filtering, sorting, and downstream handoffs—so untrusted external content can materially influence subsequent decisions.