deep-research-pro

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md workflow requires using web tools to search and "open and read the most relevant pages in full," and the README explicitly mentions DuckDuckGo search and "full-page content fetching" (including scripts/research --fetch), so the agent will fetch and interpret arbitrary public web pages (untrusted third-party content) that can directly influence its recommendations.