core-resources

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

• Third-party content exposure detected (high risk: 0.90). The skill's required templates and workflow direct the agent to perform and incorporate web research (e.g., assets/output_templates/chapter1_references.md "Chapter 1 웹 조사 결과" with "출처 URL", the prompt_template and example_prompts referencing public DBs like TCGA/HPA/ExoRbase, and execution_report.md showing "웹 검색 수행"), which clearly expects ingesting open/public third‑party content that can materially influence generation and tool actions.