ai-scientist

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the LiteratureReviewer/ResearchPipeline fetching public sources (e.g., "arxiv", "semantic-scholar", and guidance to use "pubmed") as input to literature-review steps whose outputs feed hypothesis generation, experiment design, and paper writing, so the agent ingests and acts on untrusted third-party content.