fetch-paper

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

• Third-party content exposure detected (high risk: 0.75). Yes: the required workflow resolves a DOI/arXiv ID by making runtime HTTP requests to outsider-authored public web sources (e.g., Unpaywall API responses and arXiv HTML/PDF URLs), then decodes the returned bodies into readable text/JSON that can be included in the agent’s LLM context via the skill’s human/JSON output.