literature-mapping-guide

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md includes a Python workflow that directly fetches paper metadata and references from the public Semantic Scholar API (https://api.semanticscholar.org/...) and instructs using external services (Connected Papers, Litmaps) with user-supplied seed URLs/titles, so the agent ingests open third-party content that can influence graph-building and downstream decisions.