general-deep-research

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow explicitly performs mcp_base_search_literature(..., download=True) and search_web(...), which can fetch and ingest outsider-authored full-text web/paper content (public web pages and downloaded papers) into the agent for extraction and synthesis.