podcast-blog-post-creator

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly requires the agent to search for and embed external web sources (Phase 1 Step 3: "Research hyperlink sources" citing pmc.ncbi.nlm.nih.gov and other public sites) and to verify/test hyperlinks (Phase 3 Step 3), which means the agent will fetch and interpret open/public third‑party content (guest sites, academic pages, arbitrary URLs) as part of its decision-making and linking workflow.