deep-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Info Collector workflow (SKILL.md Phase 1) and accompanying scripts (scripts/info_search_scheduler.py listing open-websearch, brave, zhipu backends) plus runtime fetch tools (scripts/research_quant_toolkit.py fetch-fred) explicitly fetch and ingest public web pages and third‑party APIs (news, blogs, search results, FRED) which are untrusted/user-generated and are read and interpreted to drive analysis and reporting decisions, creating a clear avenue for indirect prompt injection.