literature-search

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

• Third-party content exposure detected (high risk: 0.85). The skill “literature-search” is designed to fetch and compile academic content from public sources (e.g., Google Scholar/PubMed/arXiv/IEEE/ACM/Semantic) at runtime, and that fetched page/article text (outsider-authored) would be ingested into the agent’s LLM context as readable prose.