denario

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly includes literature search functionality (see SKILL.md "When to Use This Skill" and references/examples.md showing den.search_literature(...) and references/research_pipeline.md noting "Literature Search" integration), which implies the agent will fetch and read public third‑party research/web content to inform methodology and results, so external content could influence agent actions.