paper-search

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly lists public third-party sources (e.g., arxiv, pubmed, google_scholar, semantic, openalex, etc.) and the Workflow step 3 requires using read <source> <paper_id> to fetch and extract full-text papers, so the agent will ingest untrusted external content that could contain instructions influencing its behavior.