write-article

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly updates a sitemap-based cache from the public Substack archive (https://chatwithgpt.substack.com) and instructs using WebFetch to read full article content, meaning the agent will fetch and interpret untrusted, third‑party web content as part of its workflow.