imaginarii-blog-writer

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires the agent to "research if needed," "add source citations" and include "at least 3–5 external hyperlinks to sources" (see the "Input Formats", "Conversion Workflow" and "AdSense Compliance Checklist" sections), which implies fetching and interpreting open public web content as part of the writing workflow and therefore exposes the agent to untrusted third‑party content.